54 citations · 57 across the 5 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools
Yuqi Jia, Ruiqi Wang, Patrick Li +3
Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be…
cs.CR2026
AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
Yuqi Jia, Ruiqi Wang, Xilong Wang +2
Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typic…