{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:56Z","timestamp":1775815196804,"version":"3.50.1"},"reference-count":568,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002347","name":"German Federal Ministry of Education and Research (BMBF) through the project ALICE III","doi-asserted-by":"publisher","award":["01IS18049B"],"award-info":[{"award-number":["01IS18049B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Berlin Institute for the Foundations of Learning and Data (BIFOLD) sponsored by the BMBF"},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["KL 2698\/2-1"],"award-info":[{"award-number":["KL 2698\/2-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF","doi-asserted-by":"publisher","award":["01IS18051A"],"award-info":[{"award-number":["01IS18051A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF","doi-asserted-by":"publisher","award":["031B0770E"],"award-info":[{"award-number":["031B0770E"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF for the Berlin Center for Machine Learning","doi-asserted-by":"publisher","award":["01IS18037A-I"],"award-info":[{"award-number":["01IS18037A-I"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF for the Berlin Center for Machine Learning","doi-asserted-by":"publisher","award":["01IS14013A-E"],"award-info":[{"award-number":["01IS14013A-E"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF for the Berlin Center for Machine Learning","doi-asserted-by":"publisher","award":["031L0207A-D"],"award-info":[{"award-number":["031L0207A-D"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF","doi-asserted-by":"publisher","award":["01GQ1115"],"award-info":[{"award-number":["01GQ1115"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF","doi-asserted-by":"publisher","award":["01GQ0850"],"award-info":[{"award-number":["01GQ0850"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"DFG","doi-asserted-by":"publisher","award":["Math+"],"award-info":[{"award-number":["Math+"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"DFG","doi-asserted-by":"publisher","award":["EXC 2046\/1"],"award-info":[{"award-number":["EXC 2046\/1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"DFG","doi-asserted-by":"publisher","award":["Project ID 390685689"],"award-info":[{"award-number":["Project ID 390685689"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) grants funded by the Korea Government","award":["2017-0-00451"],"award-info":[{"award-number":["2017-0-00451"]}]},{"name":"Korea Government through the Artificial Intelligence Graduate School Program, Korea University","award":["2019-0-00079"],"award-info":[{"award-number":["2019-0-00079"]}]},{"DOI":"10.13039\/100000185","name":"U.S. Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR001119C0112"],"award-info":[{"award-number":["HR001119C0112"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"U.S. Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-19-C-0092"],"award-info":[{"award-number":["FA8750-19-C-0092"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"U.S. Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR001120C0022"],"award-info":[{"award-number":["HR001120C0022"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/jproc.2021.3052449","type":"journal-article","created":{"date-parts":[[2021,2,5]],"date-time":"2021-02-05T23:13:14Z","timestamp":1612566794000},"page":"756-795","source":"Crossref","is-referenced-by-count":773,"title":["A Unifying Review of Deep and Shallow Anomaly Detection"],"prefix":"10.1109","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9707-297X","authenticated-orcid":false,"given":"Lukas","family":"Ruff","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2667-513X","authenticated-orcid":false,"given":"Jacob R.","family":"Kauffmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6863-7006","authenticated-orcid":false,"given":"Robert A.","family":"Vandermeulen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-6186","authenticated-orcid":false,"given":"Gregoire","family":"Montavon","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6283-3265","authenticated-orcid":false,"given":"Wojciech","family":"Samek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6829-3725","authenticated-orcid":false,"given":"Marius","family":"Kloft","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8223-8586","authenticated-orcid":false,"given":"Thomas G.","family":"Dietterich","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3861-7685","authenticated-orcid":false,"given":"Klaus-Robert","family":"Muller","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref275","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref277","article-title":"Do deep generative models know what they don’t know?","author":"nalisnick","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185996"},{"key":"ref271","first-page":"1100","article-title":"Deep structured energy based models for anomaly detection","volume":"48","author":"zhai","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref270","first-page":"1105","article-title":"Learning deep energy models","author":"ngiam","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.08.220"},{"key":"ref273","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume":"32","author":"rezende","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref272","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1347"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0365-y"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0152173"},{"key":"ref173","first-page":"3535","article-title":"A survey of outlier detection algorithms for data streams","author":"tamboli","year":"2016","journal-title":"Proc 3rd Int Conf Comput Sustain Global Develop"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932769"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/2686378"},{"key":"ref178","author":"rousseeuw","year":"2005","journal-title":"Robust Regression &amp Outlier Detection"},{"key":"ref177","author":"barnett","year":"1994","journal-title":"Outliers in Statistical Data"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.184"},{"key":"ref267","article-title":"Your classifier is secretly an energy based model and you should treat it like one","author":"grathwohl","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref269","first-page":"448","article-title":"Deep Boltzmann machines","author":"salakhutdinov","year":"2009","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.101.075042"},{"key":"ref287","doi-asserted-by":"crossref","DOI":"10.1126\/science.aaw1147","article-title":"Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning","volume":"365","author":"no\u00e9","year":"2019","journal-title":"Science"},{"key":"ref286","first-page":"2078","article-title":"Neural autoregressive flows","volume":"80","author":"huang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref285","article-title":"Density estimation using real NVP","author":"dinh","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref181","article-title":"A survey on GANs for anomaly detection","author":"di mattia","year":"2019","journal-title":"arXiv 1906 11632"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref180","article-title":"Deep learning for anomaly detection:A survey","author":"chalapathy","year":"2019","journal-title":"arXiv 1901 03407"},{"key":"ref283","article-title":"Normalizing flows for probabilistic modeling and inference","author":"papamakarios","year":"2019","journal-title":"arXiv 1912 02762"},{"key":"ref282","article-title":"NICE: Non-linear independent components estimation","author":"dinh","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref281","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref185","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10247-4","author":"garc\u00eda","year":"2015","journal-title":"Data preprocessing techniques for data mining"},{"key":"ref280","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume":"70","author":"arjovsky","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref184","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/72.914517"},{"key":"ref182","article-title":"Deep learning for anomaly detection: A review","author":"pang","year":"2020","journal-title":"arXiv 2007 02500"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-3994-4"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.2307\/1266761"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.2307\/1266540"},{"key":"ref186","author":"rumsfeld","year":"2011","journal-title":"Known and Unknown A Memoir"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47578-3"},{"key":"ref278","first-page":"1","article-title":"Variational autoencoder based anomaly detection using reconstruction probability","volume":"2","author":"an","year":"2015","journal-title":"Spec Lect IE"},{"key":"ref279","first-page":"2234","article-title":"Improved techniques for training gans","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00326"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727309"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30490-4_56"},{"key":"ref297","first-page":"2323","article-title":"Junction tree variational autoencoder for molecular graph generation","volume":"80","author":"jin","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref296","first-page":"4666","article-title":"Adversarial text generation via feature-mover’s distance","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref299","first-page":"4255","article-title":"Efficient graph generation with graph recurrent attention networks","author":"liao","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref298","first-page":"610","article-title":"NetGAN: Generating graphs via random walks","volume":"80","author":"bojchevski","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref154","first-page":"5960","article-title":"Effective end-to-end unsupervised outlier detection via inlier priority of discriminative network","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref153","first-page":"15637","article-title":"Using self-supervised learning can improve model robustness and uncertainty","author":"hendrycks","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref156","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","author":"tack","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref155","article-title":"Classification-based anomaly detection for general data","author":"bergman","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref150","first-page":"6822","article-title":"Generative probabilistic novelty detection with adversarial autoencoders","author":"pidhorskyi","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref152","first-page":"9758","article-title":"Deep anomaly detection using geometric transformations","author":"golan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref291","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv 1411 1784"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00088"},{"key":"ref290","article-title":"Why normalizing flows fail to detect out-of-distribution data","author":"kirichenko","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref146","first-page":"173","article-title":"Group anomaly detection using deep generative models","author":"chalapathy","year":"2018","journal-title":"Proc Eur Conf Mach Learn Princ Pract Knowl Discovery Databases"},{"key":"ref147","first-page":"3","article-title":"Image anomaly detection with generative adversarial networks","author":"deecke","year":"2018","journal-title":"Proc Eur Conf Mach Learn Princ Pract Knowl Discovery Databases"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref149","article-title":"WAIC, but why? Generative ensembles for robust anomaly detection","author":"choi","year":"2018","journal-title":"arXiv 1810 01392"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967706"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.4108\/trans.sis.2013.01-03.e2"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1177\/1094428112470848"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11161"},{"key":"ref164","first-page":"307","article-title":"Outlier detection: Applications and techniques","volume":"9","author":"singh","year":"2012","journal-title":"Int J Comput Sci Issues"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxr026"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1002\/wics.6"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref160","first-page":"1","article-title":"A review of statistical outlier methods","volume":"30","author":"walfish","year":"2006","journal-title":"Pharm Technol"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1023\/B:AIRE.0000045502.10941.a9"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2003.07.018"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2003.07.019"},{"key":"ref197","first-page":"449","article-title":"One-class support measure machines for group anomaly detection","author":"muandet","year":"2013","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/2811268"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48057-2_9"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2010.235"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713048"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aa8232"},{"key":"ref196","first-page":"1071","article-title":"Group anomaly detection using flexible genre models","author":"xiong","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.1009"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178801"},{"key":"ref526","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0398-2"},{"key":"ref527","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0453-2"},{"key":"ref524","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_20"},{"key":"ref525","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2014.6816642"},{"key":"ref522","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"arXiv 1606 06565"},{"key":"ref523","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.064"},{"key":"ref520","article-title":"The doctor just won’t accept that!","author":"lipton","year":"2017","journal-title":"Proc NIPS Interpretable ML Symp"},{"key":"ref521","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"ref528","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-018-0585-7"},{"key":"ref529","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref530","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref535","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"ref536","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"key":"ref537","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2946162"},{"key":"ref538","article-title":"Deep variational semi-supervised novelty detection","author":"daniel","year":"2019","journal-title":"arXiv 1911 04971"},{"key":"ref531","first-page":"5061","article-title":"Multivariate triangular quantile maps for novelty detection","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref532","first-page":"14680","article-title":"Likelihood ratios for out-of-distribution detection","author":"ren","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref533","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","author":"serr\u00e0","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref534","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1976.10480949"},{"key":"ref539","doi-asserted-by":"publisher","DOI":"10.1145\/3396608"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5712"},{"key":"ref541","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33391-1_26"},{"key":"ref540","article-title":"Self-attentive classification-based anomaly detection in unstructured logs","author":"nedelkoski","year":"2020","journal-title":"arXiv 2008 09340"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref100","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref500","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1314"},{"key":"ref501","article-title":"Hybrid models for open set recognition","author":"zhang","year":"2020","journal-title":"arXiv 2003 12506"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1007\/s40745-018-0149-0"},{"key":"ref504","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref409","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref505","article-title":"Ensemble adversarial training: Attacks and defenses","author":"tram\u00e8r","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref502","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref407","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume":"48","author":"xie","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref503","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref408","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref508","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref405","doi-asserted-by":"publisher","DOI":"10.1515\/crll.1908.134.198"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/87.4.789"},{"key":"ref509","article-title":"On evaluating adversarial robustness","author":"carlini","year":"2019","journal-title":"arXiv 1902 06705"},{"key":"ref406","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014118"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.141"},{"key":"ref506","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.023"},{"key":"ref403","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.09.011"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00912.x"},{"key":"ref507","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","volume":"80","author":"athalye","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref404","doi-asserted-by":"publisher","DOI":"10.1515\/crll.1908.133.97"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1002\/for.3980070102"},{"key":"ref401","doi-asserted-by":"publisher","DOI":"10.3390\/app8091468"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956831"},{"key":"ref402","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33778-0_37"},{"key":"ref208","first-page":"1520","article-title":"Minimizing trust leaks for robust sybil detection","volume":"70","author":"h\u00f6ner","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-005-0200-2"},{"key":"ref400","first-page":"2751","article-title":"Connectivity-optimized representation learning via persistent homology","volume":"97","author":"hofer","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-012-0300-z"},{"key":"ref211","author":"sch\u00f6lkopf","year":"2002","journal-title":"Learning with kernels"},{"key":"ref210","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume":"97","author":"locatello","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref510","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume":"97","author":"zhang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref511","first-page":"125","article-title":"Adversarial examples are not bugs, they are features","author":"ilyas","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref512","first-page":"7375","article-title":"Out-of-distribution detection using multiple semantic label representations","author":"shalev","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref513","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume":"97","author":"hendrycks","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref418","first-page":"1613","article-title":"Weight uncertainty in neural networks","volume":"37","author":"blundell","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref514","first-page":"9157","article-title":"Reducing network agnostophobia","author":"dhamija","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref419","first-page":"9","article-title":"Deep support vector data description for unsupervised and semi-supervised anomaly detection","author":"ruff","year":"2019","journal-title":"Proc ICML Workshop Uncertainty Robustness Deep Learn"},{"key":"ref515","first-page":"13589","article-title":"Explanations can be manipulated and geometry is to blame","author":"dombrowski","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref516","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788613"},{"key":"ref517","article-title":"Toward interpretable machine learning: Transparent deep neural networks and beyond","author":"samek","year":"2020","journal-title":"arXiv 2003 07631"},{"key":"ref414","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref212","first-page":"211","article-title":"A classification framework for anomaly detection","volume":"6","author":"steinwart","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref518","doi-asserted-by":"publisher","DOI":"10.1518\/hfes.46.1.50.30392"},{"key":"ref415","author":"murphy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"ref519","first-page":"5541","article-title":"To trust or not to trust a classifier","author":"jiang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref416","author":"theodoridis","year":"2020","journal-title":"Machine Learning A Bayesian and Optimization Perspective"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176324626"},{"key":"ref417","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1069362732"},{"key":"ref410","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.015"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1507"},{"key":"ref411","first-page":"3861","article-title":"Towards k-means-friendly spaces: Simultaneous deep learning and clustering","volume":"70","author":"yang","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.3150\/09-BEJ184"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4149(97)00028-8"},{"key":"ref413","first-page":"517","article-title":"Unsupervised learning by predicting noise","volume":"70","author":"bojanowski","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/S0888-613X(03)00052-5"},{"key":"ref420","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2005.05.015"},{"key":"ref220","first-page":"665","article-title":"Learning minimum volume sets","volume":"7","author":"scott","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref222","first-page":"1494","article-title":"A loss framework for calibrated anomaly detection","author":"menon","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref221","first-page":"929","article-title":"Robust novelty detection with single-class MPM","author":"ghaoui","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3623"},{"key":"ref228","first-page":"129","article-title":"Minimum enclosing and maximum excluding machine for pattern description and discrimination","author":"liu","year":"2006","journal-title":"Proc Int Conf Pattern Recognit"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref226","first-page":"287","article-title":"On anomaly ranking and excess-mass curves","author":"goix","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref225","first-page":"659","article-title":"Scoring anomalies: A M-estimation formulation","author":"cl\u00e9men\u00e7on","year":"2013","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref224","article-title":"One-class classification","author":"tax","year":"2001"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(99)00087-2"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098052"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974973.11"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_3"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-018-2184-4"},{"key":"ref129","first-page":"1","article-title":"Clustering and unsupervised anomaly detection with $l_{2}$ normalized deep auto-encoder representations","author":"aytekin","year":"2018","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref128","article-title":"Deep autoencoding Gaussian mixture model for unsupervised anomaly detection","author":"zong","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00057"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"ref134","first-page":"4800","article-title":"Anomaly detection with multiple-hypotheses predictions","volume":"97","author":"nguyen","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref131","article-title":"Attribute restoration framework for anomaly detection","author":"huang","year":"2019","journal-title":"arXiv 1911 10676"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220083"},{"key":"ref233","article-title":"Deep anomaly detection with outlier exposure","author":"hendrycks","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00012-7_30"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging4020036"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/8501683"},{"key":"ref238","first-page":"2973","article-title":"Semi-supervised novelty detection","volume":"11","author":"blanchard","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/ISIP.2008.79"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49730-7_9"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2010.2045764"},{"key":"ref236","first-page":"703","article-title":"Analysis of learning from positive and unlabeled data","author":"du plessis","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.03.028"},{"key":"ref135","article-title":"RaPP: Novelty detection with reconstruction along projection pathway","author":"kim","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00356"},{"key":"ref137","first-page":"4390","article-title":"Deep one-class classification","volume":"80","author":"ruff","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2889273"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1398"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00301"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917862"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00829"},{"key":"ref144","article-title":"Deep semi-supervised anomaly detection","author":"ruff","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/h0071325"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976236.13"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref241","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref242","article-title":"Deep verifier networks: Verification of deep discriminative models with deep generative models","author":"che","year":"2019","journal-title":"arXiv 1911 07421"},{"key":"ref243","article-title":"Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features","author":"schirrmeister","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref244","first-page":"639","article-title":"QuantTree: Histograms for change detection in multivariate data streams","volume":"80","author":"boracchi","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref240","first-page":"3169","article-title":"Open category detection with PAC guarantees","volume":"80","author":"liu","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref248","first-page":"1803","article-title":"How to explain individual classification decisions","volume":"11","author":"baehrens","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262017091.001.0001"},{"key":"ref246","author":"quionero-candela","year":"2009","journal-title":"Dataset Shift in Machine Learning"},{"key":"ref245","first-page":"985","article-title":"Covariate shift adaptation by importance weighted cross validation","volume":"8","author":"sugiyama","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref105","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref104","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref111","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1078"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6"},{"key":"ref254","author":"jain","year":"1988","journal-title":"Algorithms for clustering data"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.270"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1017\/CCOL0521382483"},{"key":"ref253","first-page":"20","article-title":"Informal identification of outliers in medical data","volume":"1","author":"laurikkala","year":"2000","journal-title":"Proc 5th Int Workshop Intell Data Anal Med Pharmacol"},{"key":"ref257","author":"devroye","year":"1985","journal-title":"Nonparametric Density Estimation The L1 View"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19941330"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"ref259","first-page":"2529","article-title":"Robust kernel density estimation","volume":"13","author":"kim","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728190"},{"key":"ref258","author":"fr\u00fchwirth-schnatter","year":"2006","journal-title":"Finite Mixture and Markov Switching Models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704472"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/14786448708628471"},{"key":"ref14","author":"kuhn","year":"1970","journal-title":"The Structure of Scientific Revolutions"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2007.02.001"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12875-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2012.09.004"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1126\/science.aag2302"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2015.11.016"},{"key":"ref18","first-page":"1","article-title":"A survey of deep learning-based network anomaly detection","volume":"10","author":"kwon","year":"2017","journal-title":"Cluster Comput"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aaw8513"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2836950"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1371"},{"key":"ref113","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13890"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5308"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.semcancer.2018.07.001"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0172-3"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0447-x"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref260","first-page":"568","article-title":"Consistency of robust kernel density estimators","author":"vandermeulen","year":"2013","journal-title":"Proc Conf Learn Theory"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/IEA.2018.8387124"},{"key":"ref262","first-page":"109","article-title":"Massively parallel architectures for AI: NETL, Thistle, and Boltzmann machines","author":"fahlman","year":"1983","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"ref264","author":"lecun","year":"2006","journal-title":"A Tutorial on Energy-based Learning"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref266","first-page":"681","article-title":"Bayesian learning via stochastic gradient langevin dynamics","author":"welling","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref365","doi-asserted-by":"publisher","DOI":"10.2307\/2285654"},{"key":"ref559","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref364","author":"jolliffe","year":"2002","journal-title":"Principal Component Analysis"},{"key":"ref558","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.6.1129"},{"key":"ref363","first-page":"382","article-title":"Bayesian PCA","author":"bishop","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref557","doi-asserted-by":"publisher","DOI":"10.1109\/2.36"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00196"},{"key":"ref556","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref361","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3626-0"},{"key":"ref555","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","author":"krueger","year":"2020","journal-title":"arXiv 2003 00688"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"ref554","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231832"},{"key":"ref553","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref498","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2015.7344856"},{"key":"ref499","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref38","first-page":"4368","article-title":"Interpretable, multidimensional, multimodal anomaly detection with negative sampling for detection of device failure","author":"sipple","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref562","first-page":"159","article-title":"Fixing a broken ELBO","volume":"80","author":"alemi","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219845"},{"key":"ref563","article-title":"Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection","author":"park","year":"2020","journal-title":"arXiv 2005 01889"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2714135"},{"key":"ref560","doi-asserted-by":"publisher","DOI":"10.1002\/0471219282.eot142"},{"key":"ref31","article-title":"On accurate and reliable anomaly detection for gas turbine combustors: A deep learning approach","volume":"6","author":"yan","year":"2015","journal-title":"Proc Annu Conf Prognostics Health Manage Soc"},{"key":"ref359","article-title":"Recent advances in autoencoder-based representation learning","author":"tschannen","year":"2018","journal-title":"Proc Workshop Bayesian Deep Learn (NeurIPS)"},{"key":"ref561","article-title":"$\\beta$ -VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s150202774"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019428"},{"key":"ref357","article-title":"Dimensionality reduction: A comparative review","author":"van der maaten","year":"2009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2018.05.050"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.6.863"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s18082491"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1109\/5.58325"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/1475921717737051"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-56927-2"},{"key":"ref547","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref352","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46145-0_17"},{"key":"ref546","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref351","first-page":"518","article-title":"A novelty detection approach to classification","volume":"1","author":"japkowicz","year":"1995","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref549","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.2197\/ipsjtcva.1.83"},{"key":"ref548","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref353","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-39351-3"},{"key":"ref543","first-page":"7753","article-title":"Weakly-supervised disentanglement without compromises","author":"locatello","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref542","article-title":"Weakly supervised disentanglement with guarantees","author":"shu","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref545","first-page":"10709","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref350","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363226"},{"key":"ref544","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref491","first-page":"2586","article-title":"On the calibration of multiclass classification with rejection","author":"ni","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref490","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","author":"lee","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref493","first-page":"129","article-title":"Density networks","author":"mackay","year":"1998","journal-title":"Statistics and neural networks Advances at the interface"},{"key":"ref492","article-title":"Towards neural networks that provably know when they don’t know","author":"meinke","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref495","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"lee","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref494","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"liang","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref497","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref496","article-title":"Novelty detection via blurring","author":"choi","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref487","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"platt","year":"1999","journal-title":"Adv Large Margin Classifiers"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.12.014"},{"key":"ref488","first-page":"1321","article-title":"On calibration of modern neural networks","volume":"70","author":"guo","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.02.015"},{"key":"ref489","article-title":"Learning confidence for out-of-distribution detection in neural networks","author":"devries","year":"2018","journal-title":"arXiv 1802 04865"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0954410011421717"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNC.2018.8390278"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04180-8_44"},{"key":"ref550","article-title":"Contrastive training for improved out-of-distribution detection","author":"winkens","year":"2020","journal-title":"arXiv 2007 05566"},{"key":"ref349","first-page":"1073","article-title":"Active learning for anomaly and rare-category detection","author":"pelleg","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref551","article-title":"A critical analysis of self-supervision, or what we can learn from a single image","author":"asano","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2010.08.008"},{"key":"ref552","article-title":"Detecting out-of-distribution inputs to deep generative models using typicality","author":"nalisnick","year":"2019","journal-title":"Proc Workshop Bayesian Deep Learn (NeurIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1042727940"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.01.001"},{"key":"ref344","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-003-0132-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5539\/gjhs.v7n1p194"},{"key":"ref345","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983359"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.accinf.2016.04.001"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150459"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.04.007"},{"key":"ref347","article-title":"ALADIN: Active learning of anomalies to detect intrusions","author":"stokes","year":"2008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref383","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80089-9"},{"key":"ref51","article-title":"Unsupervised detection of lesions in brain MRI using constrained adversarial auto-encoders","author":"chen","year":"2018","journal-title":"Proc Med Imag Deep Learn"},{"key":"ref382","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90014-2"},{"key":"ref381","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref380","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690370209"},{"key":"ref387","first-page":"801","article-title":"Efficient sparse coding algorithms","author":"lee","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref386","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015826"},{"key":"ref385","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"ref384","doi-asserted-by":"publisher","DOI":"10.1038\/381607a0"},{"key":"ref486","first-page":"4878","article-title":"Selective classification for deep neural networks","author":"geifman","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref485","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_5"},{"key":"ref484","first-page":"537","article-title":"Support vector machines with a reject option","author":"grandvalet","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref483","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.03.010"},{"key":"ref482","first-page":"1823","article-title":"Classification with a reject option using a hinge loss","volume":"9","author":"bartlett","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref481","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1970.1054406"},{"key":"ref480","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1957.5222035"},{"key":"ref478","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"2010","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref479","article-title":"A proposal for supervised density estimation","author":"vandermeulen","year":"2020","journal-title":"Proc NeurIPS Pre-Registration Workshop"},{"key":"ref476","article-title":"How much can i trust you?—Quantifying uncertainties in explaining neural networks","author":"bykov","year":"2020","journal-title":"arXiv 2006 09000"},{"key":"ref477","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-010-0283-2"},{"key":"ref59","article-title":"Manifolds for unsupervised visual anomaly detection","author":"naud","year":"2020","journal-title":"arXiv 2006 11364"},{"key":"ref379","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(89)90049-0"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics10070451"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2919951"},{"key":"ref377","first-page":"318","article-title":"Learning internal representations by error propagation","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"ref378","first-page":"279","article-title":"Modular learning in neural networks","author":"ballard","year":"1987","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref55","first-page":"63","article-title":"Fusing unsupervised and supervised deep learning for white matter lesion segmentation","author":"baur","year":"2019","journal-title":"Proc Med Imag Deep Learn"},{"key":"ref54","article-title":"Unsupervised lesion detection in brain CT using Bayesian convolutional autoencoders","author":"pawlowski","year":"2018","journal-title":"Proc Med Imag Deep Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2870759"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837002"},{"key":"ref565","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2917669"},{"key":"ref370","first-page":"8069","article-title":"Efficient anomaly detection via matrix sketching","author":"sharan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref564","first-page":"130","article-title":"Information-theoretic measures for anomaly detection","author":"lee","year":"2001","journal-title":"Proc IEEE Symp Secur Privacy"},{"key":"ref567","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref372","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.114"},{"key":"ref566","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64283-3_24"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015417"},{"key":"ref374","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref568","first-page":"2443","article-title":"The need for open source software in machine learning","volume":"8","author":"sonnenburg","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref373","first-page":"1185","article-title":"Robust kernel principal component analysis","author":"nguyen","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref376","doi-asserted-by":"publisher","DOI":"10.1007\/BF00275687"},{"key":"ref375","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.06.017"},{"key":"ref473","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref472","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume":"48","author":"gal","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref475","first-page":"13991","article-title":"Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift","author":"ovadia","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref474","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"kendall","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref471","first-page":"1875","article-title":"On relevant dimensions in kernel feature spaces","volume":"9","author":"braun","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref470","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12026-8_29"},{"key":"ref469","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.07.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017467"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1002\/9780470434697","author":"huber","year":"2009","journal-title":"Robust Statistics"},{"key":"ref465","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198509844.001.0001","author":"pepe","year":"2003","journal-title":"The Statistical Evaluation of Medical Tests for Classification and Prediction"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s007780050006"},{"key":"ref466","doi-asserted-by":"publisher","DOI":"10.1002\/9780470906514"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000008084.60811.49"},{"key":"ref467","author":"duda","year":"1973","journal-title":"Pattern Classification and Scene Analysis"},{"key":"ref468","author":"theodoridis","year":"2009","journal-title":"Pattern Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335437"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19950597"},{"key":"ref366","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1979.10489779"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2877258"},{"key":"ref367","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.2.260"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-17876-z"},{"key":"ref368","first-page":"353","article-title":"A novel anomaly detection scheme based on principal component classifier","author":"shyu","year":"2003","journal-title":"Proc IEEE Int Conf Data Mining"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2015.7344872"},{"key":"ref369","first-page":"617","article-title":"In-network PCA and anomaly detection","author":"huang","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2008.2008216"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966273"},{"key":"ref43","first-page":"80","article-title":"Rare sound event detection using 1d convolutional recurrent neural networks","author":"lim","year":"2017","journal-title":"Proc Workshop Detection Classification Acoustic Scenes Events"},{"key":"ref460","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107198"},{"key":"ref463","doi-asserted-by":"publisher","DOI":"10.1148\/radiographics.18.5.9747612"},{"key":"ref464","doi-asserted-by":"publisher","DOI":"10.3310\/hta4050"},{"key":"ref461","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref462","article-title":"From clustering to cluster explanations via neural networks","author":"kauffmann","year":"2019","journal-title":"arXiv 1906 07633"},{"key":"ref320","first-page":"1169","article-title":"Outlier detection with one-class kernel Fisher discriminants","author":"roth","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.4.942"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxl005"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1126\/science.1117679"},{"key":"ref71","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"min","year":"2017","journal-title":"Briefings Bioinf"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-018-0066-y"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2966.2006.10327.x"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.11.030"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972771.47"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835813"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/JHEP05(2019)036"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2737941"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.101.064406"},{"key":"ref315","first-page":"503","article-title":"q-OCSVM: A q-quantile estimator for high-dimensional distributions","author":"glazer","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2036071"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1007\/11866565_30"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3508-2_8"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366287"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206997"},{"key":"ref311","first-page":"817","article-title":"Consistency and convergence rates of one-class SVMs and related algorithms","volume":"7","author":"vert","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref457","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref456","first-page":"11890","article-title":"Visualizing deep networks by optimizing with integrated gradients","volume":"2","author":"qi","year":"2019","journal-title":"Proc CVPR Workshops"},{"key":"ref455","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume":"70","author":"sundararajan","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref454","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref459","doi-asserted-by":"publisher","DOI":"10.1145\/3230666"},{"key":"ref458","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2013.132"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1033211"},{"key":"ref450","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.12.002"},{"key":"ref451","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref452","first-page":"451","article-title":"Area under the precision-recall curve: Point estimates and confidence intervals","author":"boyd","year":"2013","journal-title":"Proc Eur Conf Mach Learn Princ Pract Knowl Discovery Databases"},{"key":"ref453","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref310","first-page":"139","article-title":"One-class SVMs for document classification","volume":"2","author":"manevitz","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref60","article-title":"Anomaly detection with deep perceptual autoencoders","author":"tuluptceva","year":"2020","journal-title":"arXiv 2006 13265"},{"key":"ref62","first-page":"1961","article-title":"What’s strange about recent events (WSARE): An algorithm for the early detection of disease outbreaks","volume":"6","author":"wong","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref61","first-page":"808","article-title":"Bayesian network anomaly pattern detection for disease outbreaks","author":"wong","year":"2003","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1002\/qj.49712353910"},{"key":"ref305","first-page":"377","article-title":"Optimal single-class classification strategies","author":"el-yaniv","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2012.02.022"},{"key":"ref304","first-page":"54","article-title":"Single-class classification","author":"minter","year":"1975","journal-title":"Proc LARS Symposia"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2016.11.016"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1999.10485670"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5194\/esd-8-677-2017"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-5438-0_20"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2852302"},{"key":"ref301","first-page":"797","article-title":"One-class classifier networks for target recognition applications","author":"moya","year":"1993","journal-title":"Proc World Congr Neural Netw"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2965961"},{"key":"ref300","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/S1367-5931(02)00329-0"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1017\/S026988891300043X"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00120-4"},{"key":"ref444","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-015-0444-8"},{"key":"ref443","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788611"},{"key":"ref446","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.09.037"},{"key":"ref445","author":"rayana","year":"2016","journal-title":"ODDS Library"},{"key":"ref448","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(96)00142-2"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/72.788641"},{"key":"ref447","author":"dua","year":"2017","journal-title":"UCI Machine Learning Repository"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.52"},{"key":"ref449","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref441","first-page":"1","article-title":"UNSW-NB15: A comprehensive data set for network intrusion detection systems","author":"moustafa","year":"2015","journal-title":"Proc Mil Commun Inf Syst Conf"},{"key":"ref442","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.070"},{"key":"ref440","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553462"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref94","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1117\/12.487069"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2006.275565"},{"key":"ref340","author":"hastie","year":"2009","journal-title":"The Elements of Statistical Learning Data Mining Inference and Prediction"},{"key":"ref341","article-title":"Generating artificial outliers in the absence of genuine ones—A survey","author":"steinbuss","year":"2020","journal-title":"arXiv 2006 03646"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330871"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207209"},{"key":"ref334","article-title":"The clever Hans effect in anomaly detection","author":"kauffmann","year":"2020","journal-title":"arXiv 2006 10609"},{"key":"ref333","first-page":"11335","article-title":"DROCC: Deep robust one-class classification","author":"goyal","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref99","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv 1412 5567"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979049"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref338","article-title":"Timeseries anomaly detection using temporal hierarchical one-class network","author":"shen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref337","article-title":"Explainable deep one-class classification","author":"liznerski","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref439","doi-asserted-by":"crossref","first-page":"3784","DOI":"10.1109\/TNNLS.2017.2736643","article-title":"Credit card fraud detection: A realistic modeling and a novel learning strategy","volume":"29","author":"dal pozzolo","year":"2018","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref438","author":"zimmerer","year":"2020","journal-title":"Medical Out-of-Distribution Analysis Challenge"},{"key":"ref437","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref436","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585"},{"key":"ref435","article-title":"A PCB dataset for defects detection and classification","author":"huang","year":"2019","journal-title":"arXiv 1901 08204"},{"key":"ref434","article-title":"Natural adversarial examples","author":"hendrycks","year":"2019","journal-title":"arXiv 1907 07174"},{"key":"ref433","first-page":"1","article-title":"A meta-analysis of the anomaly detection problem","author":"emmott","year":"2016","journal-title":"arXiv 1503 01158"},{"key":"ref432","doi-asserted-by":"publisher","DOI":"10.1145\/2500853.2500858"},{"key":"ref430","doi-asserted-by":"publisher","DOI":"10.1515\/PIKO.2004.228"},{"key":"ref431","first-page":"3681","article-title":"Security analysis of online centroid anomaly detection","volume":"13","author":"kloft","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref81","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref84","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref330","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00006"},{"key":"ref332","article-title":"Rethinking assumptions in deep anomaly detection","author":"ruff","year":"2020","journal-title":"arXiv 2006 00339"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref323","first-page":"907","article-title":"A Bayesian approach to the data description problem","author":"ghasemi","year":"2012","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2329534"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013991"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_21"},{"key":"ref85","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref327","first-page":"2609","article-title":"A deep one-class neural network for anomalous event detection in complex scenes","volume":"31","author":"wu","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref429","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"hendrycks","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.483"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref88","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref328","article-title":"Anomaly detection using one-class neural networks","author":"chalapathy","year":"2018","journal-title":"arXiv 1802 06360"},{"key":"ref426","article-title":"Deep nearest neighbor anomaly detection","author":"bergman","year":"2020","journal-title":"arXiv 2002 10445"},{"key":"ref425","first-page":"2712","article-title":"Robust random cut forest based anomaly detection on streams","volume":"48","author":"guha","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref428","article-title":"MNIST-C: A robustness benchmark for computer vision","author":"mu","year":"2019","journal-title":"arXiv 1906 02337"},{"key":"ref427","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2013.37"},{"key":"ref422","first-page":"10923","article-title":"Statistical analysis of nearest neighbor methods for anomaly detection","author":"gu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref421","first-page":"2250","article-title":"Anomaly detection with score functions based on nearest neighbor graphs","author":"zhao","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref424","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref423","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2008.05.003"},{"key":"ref399","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_13"},{"key":"ref389","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.08.043"},{"key":"ref388","article-title":"k-sparse autoencoders","author":"makhzani","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref390","first-page":"136","article-title":"Why regularized auto-encoders learn sparse representation?","volume":"48","author":"arpit","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref397","article-title":"LSTM-based encoder-decoder for multi-sensor anomaly detection","author":"malhotra","year":"2016","journal-title":"arXiv 1607 00148"},{"key":"ref398","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/378"},{"key":"ref395","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801475"},{"key":"ref396","article-title":"Adversarial autoencoders","author":"makhzani","year":"2015","journal-title":"arXiv 1511 05644"},{"key":"ref393","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","author":"rifai","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref394","first-page":"540","article-title":"Unsupervised lesion detection via image restoration with a normative prior","author":"you","year":"2019","journal-title":"Proc Int Conf Med Imag Deep Learn"},{"key":"ref391","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref392","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/9420072\/09347460.pdf?arnumber=9347460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T18:24:44Z","timestamp":1724437484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9347460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":568,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2021.3052449","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}