{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:42:52Z","timestamp":1773002572861,"version":"3.50.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1934568"],"award-info":[{"award-number":["CCF-1934568"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2048280"],"award-info":[{"award-number":["IIS-2048280"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2008173"],"award-info":[{"award-number":["IIS-2008173"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2113605"],"award-info":[{"award-number":["DMS-2113605"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2210388"],"award-info":[{"award-number":["DMS-2210388"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2152289"],"award-info":[{"award-number":["DMS-2152289"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2134107"],"award-info":[{"award-number":["DMS-2134107"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cisco Faculty Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tetci.2024.3372383","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:23:53Z","timestamp":1710793433000},"page":"3654-3664","source":"Crossref","is-referenced-by-count":5,"title":["Adversarial Examples Detection With Bayesian Neural Network"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7195-5774","authenticated-orcid":false,"given":"Yao","family":"Li","sequence":"first","affiliation":[{"name":"Statistics and Operations Research Department, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1223-5922","authenticated-orcid":false,"given":"Tongyi","family":"Tang","sequence":"additional","affiliation":[{"name":"Statistics Department, University of California, Davis, Davis, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3520-9627","authenticated-orcid":false,"given":"Cho-Jui","family":"Hsieh","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7067-405X","authenticated-orcid":false,"given":"Thomas C. M.","family":"Lee","sequence":"additional","affiliation":[{"name":"Statistics Department, University of California, Davis, Davis, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref2","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref3","author":"Kurkova","year":"2018","journal-title":"Artif. Neural Netw. Mach. Learn.: 27th Int. Conf. Artif. Neural Netw."},{"key":"ref4","volume-title":"Towards Adversarial Robustness of Deep Neural Networks","author":"Yang","year":"2020"},{"key":"ref5","volume-title":"On Robustness and Efficiency of Machine Learning Systems","author":"Li","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2021.2006781"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933524"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2021.2006781"},{"key":"ref11","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Athalye","year":"2018"},{"key":"ref12","article-title":"Stochastic activation pruning for robust adversarial defense","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dhillon","year":"2018"},{"key":"ref13","article-title":"Characterizing adversarial subspaces using local intrinsic dimensionality","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2018"},{"key":"ref14","article-title":"Defense-GAN: Protecting classifiers against adversarial attacks using generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Samangouei","year":"2018"},{"key":"ref15","article-title":"PixelDefend: Leveraging generative models to understand and defend against adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2018"},{"key":"ref16","article-title":"Mitigating adversarial effects through randomization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2018"},{"key":"ref17","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Madry","year":"2018"},{"key":"ref18","article-title":"A boundary tilting persepective on the phenomenon of adversarial examples","author":"Tanay","year":"2016"},{"key":"ref19","article-title":"Detecting adversarial samples from artifacts","author":"Feinman","year":"2017"},{"key":"ref20","first-page":"7913","article-title":"Robust detection of adversarial attacks by modeling the intrinsic properties of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327369"},{"key":"ref22","first-page":"7717","article-title":"Attacks meet interpretability: Attribute-steered detection of adversarial samples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tao","year":"2018"},{"key":"ref23","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6140"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3169973"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_23"},{"key":"ref27","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Cohen","year":"2019"},{"key":"ref28","article-title":"Adv-BNN: Improved adversarial defense through robust Bayesian neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref29","first-page":"6892","article-title":"Bayesian adversarial learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye","year":"2018"},{"key":"ref30","first-page":"15602","article-title":"Robustness of Bayesian neural networks to gradient-based attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Carbone","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746230"},{"key":"ref32","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3039295"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106961"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3287624.3288750"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-019-0027-x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11302"},{"key":"ref43","volume-title":"Evaluation and Design of Robust Neural Network Defenses","author":"Carlini","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref45","article-title":"Decision-based adversarial attacks: Reliable attacks against black-box machine learning models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brendel","year":"2018"},{"key":"ref46","first-page":"2137","article-title":"Black-box adversarial attacks with limited queries and information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilyas","year":"2018"},{"key":"ref47","article-title":"Sign-OPT: A query-efficient hard-label adversarial attack","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheng","year":"2020"},{"key":"ref48","article-title":"Subspace attack: Exploiting promising subspaces for query-efficient black-box attacks","volume":"32","author":"Yan","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00045"},{"key":"ref50","volume-title":"Towards Interpretability and Robustness of Machine Learning Models","author":"Chen","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref52","article-title":"Ensemble adversarial training: Attacks and defenses","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tramr","year":"2018"},{"key":"ref53","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3103528"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134057"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00740"},{"key":"ref57","article-title":"The robust manifold defense: Adversarial training using generative models","author":"Jalal","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00740"},{"key":"ref59","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wong","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056046"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3113342"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089128"},{"key":"ref63","first-page":"1","article-title":"Challenging the adversarial robustness of DNNs based on error-correcting output codes","volume":"2020","author":"Zhang","year":"2020","journal-title":"Secur. Commun. Netw."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2978474"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_34"},{"key":"ref66","article-title":"On detecting adversarial perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Metzen","year":"2017"},{"key":"ref67","article-title":"On detecting adversarial perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Metzen","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3051529"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105238"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3593078.3593935"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP48549.2020.00021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3241428"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC55077.2022.9886997"},{"key":"ref74","first-page":"5498","article-title":"The odds are odd: A statistical test for detecting adversarial examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Roth","year":"2019"},{"key":"ref75","first-page":"8764","article-title":"A general framework for detecting anomalous inputs to DNN classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Raghuram","year":"2021"},{"key":"ref76","article-title":"Towards black-box adversarial example detection: A data reconstruction-based method","author":"Gao","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1496"},{"key":"ref78","first-page":"171","article-title":"Frequency-guided word substitutions for detecting textual adversarial examples","volume-title":"Proc. 16th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Mozes","year":"2021"},{"key":"ref79","first-page":"3656","article-title":"Detection of adversarial examples in text classification: Benchmark and baseline via robust density estimation","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Yoo","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.440"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01242-z"},{"key":"ref82","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref83","article-title":"The MNIST database of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref84","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref85","article-title":"Spectral normalization for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miyato","year":"2018"},{"key":"ref86","first-page":"5852","article-title":"Noisy natural gradient as variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02607"},{"key":"ref88","article-title":"Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning","author":"Papernot","year":"2018"},{"key":"ref89","first-page":"5546","article-title":"To trust or not to trust a classifier","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Jiang","year":"2018"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7433297\/10703967\/10472606-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10703967\/10472606.pdf?arnumber=10472606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T17:27:10Z","timestamp":1727976430000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":89,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3372383","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}