no code implementations • 16 Dec 2023 • Mengxin Zheng, Jiaqi Xue, Xun Chen, Yanshan Wang, Qian Lou, Lei Jiang
However, the security issues, e. g., Trojan attacks, of prompt tuning on a few data samples are not well-studied.
no code implementations • 16 Dec 2023 • Mengxin Zheng, Jiaqi Xue, Yi Sheng, Lei Yang, Qian Lou, Lei Jiang
TrojFair is a stealthy Fairness attack that is resilient to existing model fairness audition detectors since the model for clean inputs is fair.
no code implementations • 16 Mar 2023 • Mengxin Zheng, Jiaqi Xue, ZiHao Wang, Xun Chen, Qian Lou, Lei Jiang, XiaoFeng Wang
We evaluated SSL-Cleanse on various datasets using 1200 encoders, achieving an average detection success rate of 82. 2% on ImageNet-100.
1 code implementation • CVPR 2023 • Mengxin Zheng, Qian Lou, Lei Jiang
The success of ViTs motivates adversaries to perform backdoor attacks on ViTs.