{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T12:23:36Z","timestamp":1768911816621,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3102100"],"award-info":[{"award-number":["2022YFB3102100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U244120033"],"award-info":[{"award-number":["U244120033"]}],"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":["62402425"],"award-info":[{"award-number":["62402425"]}],"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":["62502432"],"award-info":[{"award-number":["62502432"]}],"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":["62372075"],"award-info":[{"award-number":["62372075"]}],"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":["62502433"],"award-info":[{"award-number":["62502433"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Chongqing, China","award":["CSTB2024NSCQ-LZX0084"],"award-info":[{"award-number":["CSTB2024NSCQ-LZX0084"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M762829"],"award-info":[{"award-number":["2024M762829"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tdsc.2025.3612047","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:39:45Z","timestamp":1758303585000},"page":"876-889","source":"Crossref","is-referenced-by-count":0,"title":["Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset Without Auxiliary Data"],"prefix":"10.1109","volume":"23","author":[{"given":"Yuwen","family":"Pu","sequence":"first","affiliation":[{"name":"School of Big Data & Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5894-662X","authenticated-orcid":false,"given":"Jiahao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0081-0946","authenticated-orcid":false,"given":"Chunyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Big Data & Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5301-7019","authenticated-orcid":false,"given":"Zhou","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6085-7300","authenticated-orcid":false,"given":"Qingming","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5825-2241","authenticated-orcid":false,"given":"Chunqiang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Big Data & Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4268-372X","authenticated-orcid":false,"given":"Shouling","family":"Ji","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2987958"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3053128"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3585385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-8059-5_36"},{"key":"ref7","article-title":"Data poisoning won\u2019t save you from facial recognition","author":"Radiya-Dixit","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-42921-8_10"},{"key":"ref9","article-title":"Rethinking the vulnerabilities of face recognition systems: From a practical perspective","author":"Chen","year":"2024"},{"key":"ref10","article-title":"Artificial intelligence act","year":"2024"},{"key":"ref11","article-title":"Digital services act","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3182979"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909068"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/96"},{"key":"ref15","first-page":"6399","article-title":"FreeEagle: Detecting complex neural trojans in data-free cases","volume-title":"Proc. USENIX Secur. Symp.","author":"Fu"},{"key":"ref16","article-title":"A stealthy backdoor attack for without-label-sharing split learning","author":"Pu","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00959"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209199"},{"key":"ref20","first-page":"2725","article-title":"ASSET: Robust backdoor data detection across a multiplicity of deep learning paradigms","volume-title":"Proc. USENIX Secur. Symp.","author":"Pan"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.23171"},{"key":"ref22","first-page":"14900","article-title":"Anti-backdoor learning: Training clean models on poisoned data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref23","first-page":"9727","article-title":"Effective backdoor defense by exploiting sensitivity of poisoned samples","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref24","first-page":"1685","article-title":"Towards a proactive ML approach for detecting backdoor poison samples","volume-title":"Proc. USENIX Secur. Symp.","author":"Qi"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2023.3329426"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3175616"},{"key":"ref27","article-title":"How to sift out a clean data subset in the presence of data poisoning?","author":"Zeng","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_11"},{"key":"ref29","article-title":"Targeted backdoor attacks on deep learning systems using data poisoning","author":"Chen","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23291"},{"key":"ref32","first-page":"6106","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shafahi"},{"key":"ref33","article-title":"Clean-label backdoor attacks","author":"Turner","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2020.3021407"},{"key":"ref35","first-page":"7614","article-title":"Transferable clean-label poisoning attacks on deep neural nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6871"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087237"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/sp54263.2024.00226"},{"key":"ref39","article-title":"Neural polarizer: A lightweight and effective backdoor defense via purifying poisoned features","author":"Zhu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.23069"},{"key":"ref41","article-title":"Shared adversarial unlearning: Backdoor mitigation by unlearning shared adversarial examples","author":"Wei","year":"2023"},{"key":"ref42","first-page":"11973","article-title":"On the trade-off between adversarial and backdoor robustness","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Weng"},{"key":"ref43","article-title":"Does adversarial robustness really imply backdoor vulnerability?","author":"Gao","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3312973"},{"key":"ref45","article-title":"Backdoor defense via decoupling the training process","author":"Huang","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01963"},{"key":"ref47","first-page":"1541","article-title":"Demon in the variant: Statistical analysis of DNNs for robust backdoor contamination detection","volume-title":"Proc. USENIX Secur. Symp.","author":"Tang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01569"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3326983"},{"key":"ref50","article-title":"Backdoor attack in the physical world","author":"Li","year":"2021"},{"key":"ref51","article-title":"WaNet\u2013imperceptible warping-based backdoor attack","author":"Nguyen","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802997"},{"key":"ref53","article-title":"Revisiting the assumption of latent separability for backdoor defenses","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qi"},{"key":"ref54","article-title":"SCALE-UP: An efficient black-box input-level backdoor detection via analyzing scaled prediction consistency","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo"},{"key":"ref55","first-page":"16216","article-title":"Rethinking backdoor attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Khaddaj"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3281872"},{"key":"ref57","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref58","article-title":"AEVA: Black-box backdoor detection using adversarial extreme value analysis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo"},{"key":"ref59","article-title":"SCALE-UP: An efficient black-box input-level backdoor detection via analyzing scaled prediction consistency","author":"Guo","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2025.230478"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/INFOo11020108"},{"issue":"7","key":"ref62","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref63","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414862"},{"key":"ref66","article-title":"BaDExpert: Extracting backdoor functionality for accurate backdoor input detection","author":"Xie","year":"2023"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8858\/11354469\/11173939.pdf?arnumber=11173939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:57:47Z","timestamp":1768856267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11173939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":66,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2025.3612047","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}