{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:03:18Z","timestamp":1784300598272,"version":"3.55.0"},"reference-count":337,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836014"],"award-info":[{"award-number":["61836014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222609"],"award-info":[{"award-number":["62222609"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076236"],"award-info":[{"award-number":["62076236"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61721004"],"award-info":[{"award-number":["61721004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276134"],"award-info":[{"award-number":["62276134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Key Research Program of Frontier Sciences of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["ZDBS-LY-7004"],"award-info":[{"award-number":["ZDBS-LY-7004"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2019141"],"award-info":[{"award-number":["2019141"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/jproc.2023.3238024","type":"journal-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:44:58Z","timestamp":1674845098000},"page":"185-215","source":"Crossref","is-referenced-by-count":45,"title":["A Survey on Learning to Reject"],"prefix":"10.1109","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9260-188X","authenticated-orcid":false,"given":"Xu-Yao","family":"Zhang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5487-9845","authenticated-orcid":false,"given":"Guo-Sen","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3377-892X","authenticated-orcid":false,"given":"Xiuli","family":"Li","sequence":"additional","affiliation":[{"name":"Deepwise Artificial Intelligence Lab, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5990-7307","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6743-4175","authenticated-orcid":false,"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Detecting out-of-distribution inputs in deep neural networks using an early-layer output","author":"Abdelzad","year":"2019","journal-title":"arXiv:1910.10307"},{"key":"ref2","first-page":"38","article-title":"Protecting world leaders against deep fakes","volume-title":"Proc. CVPR Workshops","author":"Agarwal"},{"key":"ref3","first-page":"1","article-title":"Detecting adversarial examples and other misclassifications in neural networks by introspection","volume-title":"Proc. ICML Workshop Uncertainty Robustness Deep Learn.","author":"Aigrain"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2019.12.009"},{"key":"ref5","article-title":"FOOD: Fast out-of-distribution detector","author":"Amit","year":"2020","journal-title":"arXiv:2008.06856"},{"key":"ref6","first-page":"356","article-title":"NADS: Neural architecture distribution search for uncertainty awareness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ardywibowo"},{"key":"ref7","article-title":"Confidence from invariance to image transformations","author":"Bahat","year":"2018","journal-title":"arXiv:1804.00657"},{"key":"ref8","article-title":"Classification confidence estimation with test-time data-augmentation","author":"Bahat","year":"2020","journal-title":"arXiv:2006.16705"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11672"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.299"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/34.709564"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref15","first-page":"1","article-title":"Classification-based anomaly detection for general data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bergman"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19941330"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220401"},{"key":"ref19","first-page":"1613","article-title":"Weight uncertainty in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2018.8698539"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269260"},{"key":"ref22","first-page":"1","article-title":"Decision-based adversarial attacks: Reliable attacks against black-box machine learning models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Brendel"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101653"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2973258"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"ref32","first-page":"1467","article-title":"Confidence scoring using whitebox meta-models with linear classifier probes","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Chen"},{"key":"ref33","article-title":"WAIC, but why? Generative ensembles for robust anomaly detection","author":"Choi","year":"2018","journal-title":"arXiv:1810.01392"},{"key":"ref34","first-page":"1","article-title":"Novelty detection via blurring","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Choi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1957.5222035"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1970.1054406"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3009287"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3675-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.011"},{"key":"ref40","first-page":"2898","article-title":"Addressing failure prediction by learning model confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Corbiere"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3085983"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/72.410358"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00489"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46379-7_5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(94)90065-5"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MSEC.2021.3076443"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00120"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/2987588"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom45495.2020.9127389"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00103"},{"key":"ref53","article-title":"Improving reconstruction autoencoder out-of-distribution detection with Mahalanobis distance","author":"Denouden","year":"2018","journal-title":"arXiv:1812.02765"},{"key":"ref54","article-title":"Learning confidence for out-of-distribution detection in neural networks","author":"DeVries","year":"2018","journal-title":"arXiv:1802.04865"},{"key":"ref55","first-page":"9175","article-title":"Reducing network agnostophobia","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Dhamija"},{"key":"ref56","first-page":"1","article-title":"Stochastic activation pruning for robust adversarial defense","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dhillon"},{"key":"ref57","article-title":"Evaluation of neural network uncertainty estimation with application to resource-constrained platforms","author":"Ding","year":"2019","journal-title":"arXiv:1903.02050"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00010"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411892"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00897"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(93)90097-G"},{"issue":"5","key":"ref62","first-page":"1605","article-title":"On the foundations of noise-free selective classification","volume":"11","author":"El-Yaniv","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00162"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/MITP.2020.2977589"},{"key":"ref67","first-page":"1963","article-title":"On discriminative learning of prediction uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franc"},{"key":"ref68","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frank"},{"key":"ref69","first-page":"148","article-title":"Experiments with a new boosting algorithm","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Freund"},{"key":"ref70","volume-title":"Introduction to Statistical Pattern Recognition","author":"Fukunaga","year":"1990"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.42"},{"key":"ref73","first-page":"4878","article-title":"Selective classification for deep neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Geifman"},{"key":"ref74","first-page":"2151","article-title":"SelectiveNet: A deep neural network with an integrated reject option","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Geifman"},{"key":"ref75","first-page":"1","article-title":"Bias-reduced uncertainty estimation for deep neural classifiers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Geifman"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2978199"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2478\/jagi-2014-0001"},{"key":"ref79","first-page":"1","article-title":"Deep anomaly detection using geometric transformations","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Golan"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/34.598237"},{"key":"ref81","article-title":"Adversarial and clean data are not twins","author":"Gong","year":"2017","journal-title":"arXiv:1704.04960"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref83","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Goodfellow"},{"key":"ref84","first-page":"3711","article-title":"DROCC: Deep robust one-class classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.239"},{"key":"ref86","volume-title":"Think Again: The Power Knowing What You Dont Know, Viking","author":"Grant","year":"2021"},{"key":"ref87","article-title":"Towards deep neural network architectures robust to adversarial examples","author":"Gu","year":"2014","journal-title":"arXiv:1412.5068"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-291"},{"key":"ref90","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref91","first-page":"1","article-title":"Countering adversarial images using input transformations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.05.084"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00071"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/34.601248"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.learninstruc.2012.10.001"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106984"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533442"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905689"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.learninstruc.2012.05.009"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00068"},{"issue":"7777","key":"ref101","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1038\/d41586-019-03013-5","article-title":"Deep trouble for deep learning","volume":"574","author":"Heaven","year":"2019","journal-title":"Nature"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500495"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1970.300339"},{"key":"ref105","article-title":"Scaling out-of-distribution detection for real-world settings","author":"Hendrycks","year":"2019","journal-title":"arXiv:1911.11132"},{"key":"ref106","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref107","first-page":"1","article-title":"Early methods for detecting adversarial images","volume-title":"Proc. ICLR Workshop","author":"Hendrycks"},{"key":"ref108","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hendrycks"},{"key":"ref109","first-page":"1","article-title":"Deep anomaly detection with outlier exposure","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref110","first-page":"1","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Hendrycks"},{"key":"ref111","first-page":"1","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1023\/B:AIRE.0000045502.10941.a9"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911075"},{"key":"ref114","article-title":"Blocking transferability of adversarial examples in black-box learning systems","author":"Hosseini","year":"2017","journal-title":"arXiv:1703.04318"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"ref116","article-title":"Feature space singularity for out-of-distribution detection","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Huang"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16254"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00339"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.188"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00283"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00132"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00515"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3086109"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00624"},{"key":"ref125","first-page":"1","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref126","first-page":"5541","article-title":"To trust or not to trust a classifier","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000291"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5610-8"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2019.00044"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00336"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00472"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00111"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref135","first-page":"5436","article-title":"Being Bayesian, even just a bit, fixes overconfidence in ReLU networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kristiadi"},{"key":"ref136","first-page":"623","article-title":"Beta calibration: A well-founded and easily implemented improvement on logistic calibration for binary classifiers","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kull"},{"key":"ref137","first-page":"1","article-title":"Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Kull"},{"key":"ref138","first-page":"1","article-title":"Verified uncertainty calibration","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref139","article-title":"Calibration of encoder decoder models for neural machine translation","author":"Kumar","year":"2019","journal-title":"arXiv:1903.00802"},{"key":"ref140","first-page":"2805","article-title":"Trainable calibration measures for neural networks from kernel mean embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref141","first-page":"1","article-title":"Adversarial examples in the physical world","volume-title":"Proc. Workshop Track ICLR","author":"Kurakin"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.249"},{"key":"ref143","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref144","first-page":"145","article-title":"Probability calibration trees","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Leathart"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403189"},{"key":"ref147","first-page":"1","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref148","first-page":"1","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-17876-z"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00573"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01323"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3182979"},{"key":"ref154","article-title":"Hiding faces in plain sight: Disrupting AI face synthesis with adversarial perturbations","author":"Li","year":"2019","journal-title":"arXiv:1906.09288"},{"key":"ref155","first-page":"1","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00191"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.05.013"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-003-0199-5"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00496"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220027"},{"key":"ref162","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00095"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.56"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793611"},{"key":"ref168","first-page":"1","article-title":"Characterizing adversarial subspaces using local intrinsic dimensionality","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref169","first-page":"13153","article-title":"A simple baseline for Bayesian uncertainty in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Maddox"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01022"},{"key":"ref172","article-title":"Distance-based confidence score for neural network classifiers","author":"Mandelbaum","year":"2017","journal-title":"arXiv:1709.09844"},{"key":"ref173","article-title":"Metric learning for novelty and anomaly detection","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Masana"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9569"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134057"},{"key":"ref177","first-page":"1","article-title":"Predicting accurate probabilities with a ranking loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Menon"},{"key":"ref178","first-page":"1","article-title":"On detecting adversarial perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Metzen"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref181","first-page":"7034","article-title":"Confidence-aware learning for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Moon"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref184","first-page":"1","article-title":"Unsupervised temperature scaling: An unsupervised post-processing calibration method of deep networks","volume-title":"Proc. ICML Workshop Uncertainty Robustness Deep Learn.","author":"Mozafari"},{"key":"ref185","article-title":"Attended temperature scaling: A practical approach for calibrating deep neural networks","author":"Mozafari","year":"2018","journal-title":"arXiv:1810.11586"},{"key":"ref186","first-page":"1","article-title":"Calibrating deep neural networks using focal loss","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Mukhoti"},{"key":"ref187","first-page":"1","article-title":"When does label smoothing help?","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"M\u00fcller"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00348"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974348.30"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0047"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref192","first-page":"1","article-title":"Do deep generative models know what they dont know?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nalisnick"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00034"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_38"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00103"},{"key":"ref196","first-page":"1","article-title":"Relaxed softmax: Efficient confidence auto-calibration for safe pedestrian detection","volume-title":"Proc. NIPS Workshop Mach. Learn. Intell. Transp. Syst.","author":"Neumann"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref198","article-title":"Deep learning for deepfakes creation and detection: A survey","author":"Nguyen","year":"2019","journal-title":"arXiv:1909.11573"},{"key":"ref199","first-page":"1","article-title":"On the calibration of multiclass classification with rejection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ni"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102430"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3093446"},{"key":"ref202","first-page":"38","article-title":"Measuring calibration in deep learning","volume-title":"Proc. CVPR Workshops","author":"Nixon"},{"key":"ref203","article-title":"Not all failure modes are created equal: Training deep neural networks for explicable (mis)classification","author":"Olmo","year":"2020","journal-title":"arXiv:2006.14841"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00509"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2774300"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00282"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380154"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref210","article-title":"Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning","author":"Papernot","year":"2018","journal-title":"arXiv:1803.04765"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2189205"},{"key":"ref216","first-page":"234","article-title":"Uncertainty in neural networks: Approximately Bayesian ensembling","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Pearce"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01183"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00301"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01181"},{"key":"ref220","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"Pereyra","year":"2017","journal-title":"arXiv:1701.06548"},{"key":"ref221","article-title":"Calibrating uncertainties in object localization task","author":"Phan","year":"2018","journal-title":"arXiv:1811.11210"},{"key":"ref222","first-page":"6823","article-title":"Generative probabilistic novelty detection with adversarial autoencoders","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Pidhorskyi"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026"},{"issue":"3","key":"ref224","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":"ref225","first-page":"445","article-title":"The case against accuracy estimation for comparing induction algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Provost"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00491"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2991378"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00669"},{"key":"ref229","first-page":"1","article-title":"Intra order-preserving functions for calibration of multi-class neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Rahimi"},{"key":"ref230","article-title":"Harnessing model uncertainty for detecting adversarial examples","volume-title":"Proc. NIPS Workshop Bayesian Deep Learn.","author":"Rawat"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref232","first-page":"1","article-title":"Likelihood ratios for out-of-distribution detection","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2020.06.035"},{"key":"ref234","first-page":"1","article-title":"Deep Bayesian bandits showdown: An empirical comparison of Bayesian deep networks for Thompson sampling","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Riquelme"},{"key":"ref235","article-title":"Are out-of-distribution detection methods effective on large-scale datasets?","author":"Roady","year":"2019","journal-title":"arXiv:1910.14034"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2707495"},{"key":"ref237","first-page":"4393","article-title":"Deep one-class classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ruff"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00356"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref240","first-page":"1","article-title":"Defense-GAN: Protecting classifiers against adversarial attacks using generative models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Samangouei"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198850"},{"key":"ref242","first-page":"8491","article-title":"Detecting out-of-distribution examples with Gram matrices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sastry"},{"key":"ref243","volume-title":"Deep fakes and national security","author":"Sayler","year":"2020"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.54"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"ref248","first-page":"582","article-title":"Support vector method for novelty detection","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Scholkopf"},{"key":"ref249","article-title":"Adversarial learning of deepfakes in accounting","author":"Schreyer","year":"2019","journal-title":"arXiv:1910.03810"},{"key":"ref250","first-page":"1022","article-title":"Can you trust this prediction? Auditing pointwise reliability after learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Schulam"},{"key":"ref251","article-title":"From black-box to white-box: Examining confidence calibration under different conditions","volume-title":"Proc. AAAI Workshop SafeAI","author":"Schwaiger"},{"key":"ref252","first-page":"1","article-title":"SSD: A unified framework for self-supervised outlier detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sehwag"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00924"},{"key":"ref254","first-page":"1","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Serra"},{"key":"ref255","article-title":"A less biased evaluation of out-of-distribution sample detectors","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Shafaei"},{"key":"ref256","first-page":"6106","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Shafahi"},{"key":"ref257","first-page":"1","article-title":"Out-of-distribution detection using multiple semantic label representations","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Shalev"},{"key":"ref258","first-page":"1589","article-title":"Fawkes: Protecting privacy against unauthorized deep learning models","volume-title":"Proc. USENIX Secur. Symp.","author":"Shan"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1314"},{"key":"ref260","article-title":"On deep neural network calibration by regularization and its impact on refinement","author":"Singh","year":"2021","journal-title":"arXiv:2106.09385"},{"key":"ref261","article-title":"On calibration of scene-text recognition models","author":"Slossberg","year":"2020","journal-title":"arXiv:2012.12643"},{"key":"ref262","first-page":"1","article-title":"PixelDefend: Leveraging generative models to understand and defend against adversarial examples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909876"},{"key":"ref264","article-title":"Building robust classifiers through generation of confident out of distribution examples","volume-title":"Proc. NeurIPS Workshop Bayesian Deep Learn.","author":"Sricharan"},{"issue":"1","key":"ref265","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/5326.827457"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01232-x"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"ref270","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Szegedy"},{"key":"ref271","first-page":"11839","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Tack"},{"key":"ref272","volume-title":"One-class classification: Concept-learning in the absence of counter-examples","author":"Tax","year":"2001"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000008084.60811.49"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_4"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19448-8"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053195"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.2172\/1525811"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"ref279","first-page":"1","article-title":"Ensemble adversarial training: Attacks and defenses","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tramer"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.5555\/3241094.3241142"},{"key":"ref281","first-page":"14660","article-title":"Bayesian layers: A module for neural network uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tran"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414153"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3002101"},{"key":"ref285","article-title":"Out-of-distribution detection in classifiers via generation","volume-title":"Proc. NeurIPS Workshop Saf. Robustness Decis. Making","author":"Vernekar"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_34"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01468"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/476"},{"key":"ref289","article-title":"Safer classification by synthesis","author":"Wang","year":"2017","journal-title":"arXiv:1711.08534"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2895794"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00928"},{"key":"ref292","first-page":"1","article-title":"Distance metric learning for large margin nearest neighbor classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Weinberger"},{"key":"ref293","first-page":"178","article-title":"Non-parametric calibration for classification","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Wenger"},{"key":"ref294","article-title":"Adversarial examples in modern machine learning: A review","author":"Wiyatno","year":"2019","journal-title":"arXiv:1911.05268"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2044470"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"ref298","first-page":"975","article-title":"Probability estimates for multi-class classification by pairwise coupling","volume":"5","author":"Wu","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.177"},{"key":"ref300","first-page":"1","article-title":"Mitigating adversarial effects through randomization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3025308"},{"key":"ref303","first-page":"1","article-title":"Distance-based learning from errors for confidence calibration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xing"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1211-x"},{"key":"ref305","article-title":"Face transfer with generative adversarial network","author":"Xu","year":"2017","journal-title":"arXiv:1710.06090"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23198"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3045937"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1145\/3426020.3426076"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045079"},{"key":"ref310","first-page":"1","article-title":"ME-Net: Towards effective adversarial robustness with matrix estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00414"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"key":"ref314","article-title":"Artificial fingerprinting for generative models: Rooting deepfake attribution in training data","author":"Yu","year":"2020","journal-title":"arXiv:2007.08457"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00961"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/469"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00066"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref319","first-page":"609","article-title":"Obtaining calibrated probability estimates from decision trees and Naive Bayesian classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zadrozny"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775151"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_7"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2613924"},{"key":"ref323","first-page":"11117","article-title":"Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933524"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3040950"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015335"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-496"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2989782"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref330","article-title":"Learning self-consistency for deepfake detection","author":"Zhao","year":"2020","journal-title":"arXiv:2012.09311"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00126"},{"key":"ref332","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2983593"},{"key":"ref333","first-page":"1939","article-title":"Accurate probability calibration for multiple classifiers","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Zhong"},{"key":"ref334","doi-asserted-by":"publisher","DOI":"10.1145\/3395046"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_30"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"ref337","first-page":"1","article-title":"Deep autoencoding Gaussian mixture model for unsupervised anomaly detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zong"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/10038314\/10028760.pdf?arnumber=10028760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T16:22:56Z","timestamp":1709396576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10028760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":337,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2023.3238024","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}