5 papers
Fast and Lightweight Backdoor Detection via Head Random Probing
Yinbo Yu, Xueyu Yin, Jing Fang +4
Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data, gradients, or iterative trigge…
Lightweight and Fast Backdoor Model Detection
Yinbo Yu, Jing Fang, Xuewen Zhang +4
Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly analysis or trigger…
BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
Jing Fang, Saihao Yan, Xueyu Yin +3
Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will p…
A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
Yinbo Yu, Saihao Yan, Jiajia Liu
Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will p…
TAPFixer: Automatic Detection and Repair of Home Automation Vulnerabilities based on Negated-property Reasoning
Yinbo Yu, Yuanqi Xu, Kepu Huang +1
Trigger-Action Programming (TAP) is a popular end-user programming framework in the home automation (HA) system, which eases users to customize home automation and control devices…