关注
Siyuan Cheng
Siyuan Cheng
在 purdue.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Deep feature space trojan attack of neural networks by controlled detoxification
S Cheng, Y Liu, S Ma, X Zhang
Proceedings of the AAAI Conference on Artificial Intelligence 35 (2), 1148-1156, 2021
1402021
Backdoor scanning for deep neural networks through k-arm optimization
G Shen, Y Liu, G Tao, S An, Q Xu, S Cheng, S Ma, X Zhang
International Conference on Machine Learning, 9525-9536, 2021
1082021
Towards feature space adversarial attack by style perturbation
Q Xu, G Tao, S Cheng, X Zhang
Proceedings of the AAAI Conference on Artificial Intelligence 35 (12), 10523 …, 2021
54*2021
Flip: A provable defense framework for backdoor mitigation in federated learning
K Zhang, G Tao, Q Xu, S Cheng, S An, Y Liu, S Feng, G Shen, PY Chen, ...
ICLR 2023 (Best Paper Award at ECCV 2022 AROW Workshop), 2022
352022
Detecting backdoors in pre-trained encoders
S Feng, G Tao, S Cheng, G Shen, X Xu, Y Liu, K Zhang, S Ma, X Zhang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
282023
Backdoor vulnerabilities in normally trained deep learning models
G Tao, Z Wang, S Cheng, S Ma, S An, Y Liu, G Shen, Z Zhang, Y Mao, ...
arXiv preprint arXiv:2211.15929, 2022
142022
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
S Cheng, G Tao, Y Liu, S An, X Xu, S Feng, G Shen, K Zhang, Q Xu, S Ma, ...
30th Annual Network And Distributed System Security Symposium (NDSS 2023), 2023
112023
On large language models’ resilience to coercive interrogation
Z Zhang, G Shen, G Tao, S Cheng, X Zhang
2024 IEEE Symposium on Security and Privacy (SP), 252-252, 2024
10*2024
Elijah: Eliminating backdoors injected in diffusion models via distribution shift
S An, SY Chou, K Zhang, Q Xu, G Tao, G Shen, S Cheng, S Ma, PY Chen, ...
Proceedings of the AAAI Conference on Artificial Intelligence 38 (10), 10847 …, 2024
8*2024
Medic: Remove model backdoors via importance driven cloning
Q Xu, G Tao, J Honorio, Y Liu, S An, G Shen, S Cheng, X Zhang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
8*2023
Opening a Pandora's box: things you should know in the era of custom GPTs
G Tao, S Cheng, Z Zhang, J Zhu, G Shen, X Zhang
arXiv preprint arXiv:2401.00905, 2023
62023
Improving binary code similarity transformer models by semantics-driven instruction deemphasis
X Xu, S Feng, Y Ye, G Shen, Z Su, S Cheng, G Tao, Q Shi, Z Zhang, ...
Proceedings of the 32nd ACM SIGSOFT International Symposium on Software …, 2023
62023
Hard-label black-box universal adversarial patch attack
G Tao, S An, S Cheng, G Shen, X Zhang
32nd USENIX Security Symposium (USENIX Security 23), 697-714, 2023
52023
Lmpa: Improving decompilation by synergy of large language model and program analysis
X Xu, Z Zhang, S Feng, Y Ye, Z Su, N Jiang, S Cheng, L Tan, X Zhang
arXiv preprint arXiv:2306.02546, 2023
52023
Deck: Model hardening for defending pervasive backdoors
G Tao, Y Liu, S Cheng, S An, Z Zhang, Q Xu, G Shen, X Zhang
arXiv preprint arXiv:2206.09272, 2022
52022
Django: Detecting trojans in object detection models via gaussian focus calibration
G Shen, S Cheng, G Tao, K Zhang, Y Liu, S An, S Ma, X Zhang
Advances in Neural Information Processing Systems 36, 2024
32024
Rapid optimization for jailbreaking llms via subconscious exploitation and echopraxia
G Shen, S Cheng, K Zhang, G Tao, S An, L Yan, Z Zhang, S Ma, X Zhang
arXiv preprint arXiv:2402.05467, 2024
32024
: Detoxing Deep Learning Dataset
L Yan, S Cheng, G Shen, G Tao, X Chen, K Zhang, Y Mao, X Zhang
NeurIPS 2023 Workshop on Backdoors in Deep Learning-The Good, the Bad, and …, 2023
32023
Lotus: Evasive and resilient backdoor attacks through sub-partitioning
S Cheng, G Tao, Y Liu, G Shen, S An, S Feng, X Xu, K Zhang, S Ma, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
22024
Exploring the Orthogonality and Linearity of Backdoor Attacks
K Zhang, S Cheng, G Shen, G Tao, S An, A Makur, S Ma, X Zhang
2024 IEEE Symposium on Security and Privacy (SP), 225-225, 2024
12024
系统目前无法执行此操作,请稍后再试。
文章 1–20