1. Eugene Bagdasaryan and Vitaly Shmatikov . 2021 . Blind Backdoors in Deep Learning Models. In 30th USENIX Security Symposium, USENIX Security 2021 , August 11-13, 2021. USENIX Association, 1505–1521. https://www.usenix.org/conference/usenixsecurity21/presentation/bagdasaryan Eugene Bagdasaryan and Vitaly Shmatikov. 2021. Blind Backdoors in Deep Learning Models. In 30th USENIX Security Symposium, USENIX Security 2021, August 11-13, 2021. USENIX Association, 1505–1521. https://www.usenix.org/conference/usenixsecurity21/presentation/bagdasaryan
2. Provable Defense against Backdoor Policies in Reinforcement Learning;Bharti Shubham;Advances in Neural Information Processing Systems,2022
3. Why Deep Learning Works: A Manifold Disentanglement Perspective
4. Randomized channel shuffling: Minimal-overhead backdoor attack detection without clean datasets;Cai Ruisi;Advances in Neural Information Processing Systems,2022
5. Bryant Chen , Wilka Carvalho , Nathalie Baracaldo , Heiko Ludwig , Benjamin Edwards , Taesung Lee , Ian M. Molloy , and Biplav Srivastava . 2019. Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering . In Workshop on Artificial Intelligence Safety 2019 co-located with the Thirty-Third AAAI Conference on Artificial Intelligence 2019 (AAAI-19) , Honolulu, Hawaii , January 27, 2019 (CEUR Workshop Proceedings, Vol. 2301). CEUR-WS. org. https://ceur-ws.org/Vol-2301/paper_18.pdf Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian M. Molloy, and Biplav Srivastava. 2019. Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering. In Workshop on Artificial Intelligence Safety 2019 co-located with the Thirty-Third AAAI Conference on Artificial Intelligence 2019 (AAAI-19), Honolulu, Hawaii, January 27, 2019(CEUR Workshop Proceedings, Vol. 2301). CEUR-WS.org. https://ceur-ws.org/Vol-2301/paper_18.pdf