ICML Poster "backdoor attacks" Papers
6 papers found
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
Wenhan Yang, Jingdong Gao, Baharan Mirzasoleiman
ICML 2024poster
Causality Based Front-door Defense Against Backdoor Attack on Language Models
Yiran Liu, Xiaoang Xu, Zhiyi Hou et al.
ICML 2024poster
Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
Xingyi Zhao, Depeng Xu, Shuhan Yuan
ICML 2024poster
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
Linshan Hou, Ruili Feng, Zhongyun Hua et al.
ICML 2024poster
SHINE: Shielding Backdoors in Deep Reinforcement Learning
Zhuowen Yuan, Wenbo Guo, Jinyuan Jia et al.
ICML 2024poster
TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
Yichuan Mo, Hui Huang, Mingjie Li et al.
ICML 2024poster