62 citations · 80 across the 9 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024★ 1 cited
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Zhen Xiang, Linzhi Zheng, Yanjie Li +9
The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail ag…
cs.LG2023★ 1 cited
CBD: A Certified Backdoor Detector Based on Local Dominant Probability
Zhen Xiang, Zidi Xiong, Bo Li
Backdoor attack is a common threat to deep neural networks. During testing, samples embedded with a backdoor trigger will be misclassified as an adversarial target by a backdoored…
cs.LG2023★ 3 cited
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
Zhen Xiang, Zidi Xiong, Bo Li
Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversa…