Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack

25 May 2024

Papers citing "Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack"

6 / 6 papers shown

Title
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models Siyuan Liang Jiayang Liu Jiecheng Zhai Tianmeng Fang Rongcheng Tu A. Liu Xiaochun Cao Dacheng Tao VGen 49 0 0 22 Apr 2025
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework X. U. Wang Siyuan Liang Dongping Liao Han Fang Aishan Liu Xiaochun Cao Yu-liang Lu E. Chang X. Gao AAML 46 1 0 21 Mar 2025
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers Shengyuan Yang Jiawang Bai Kuofeng Gao Yong-Liang Yang Yiming Li Shu-Tao Xia AAML SILM 19 5 0 17 May 2024
Effectiveness Assessment of Recent Large Vision-Language Models Yao Jiang Xinyu Yan Ge-Peng Ji Keren Fu Meijun Sun Huan Xiong Deng-Ping Fan Fahad Shahbaz Khan 24 14 0 07 Mar 2024
Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks Wenhan Yang Jingdong Gao Baharan Mirzasoleiman VLM 100 17 0 13 Mar 2023
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic Hang Wang Zhen Xiang David J. Miller G. Kesidis AAML 22 40 0 13 May 2022