"llm agent security" Papers
2 papers found
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
Kanghua Mo, Li Hu, Yucheng Long et al.
NeurIPS 2025posterarXiv:2508.02110
4
citations
Memory Injection Attacks on LLM Agents via Query-Only Interaction
Shen Dong, Shaochen Xu, Pengfei He et al.
NeurIPS 2025posterarXiv:2503.03704
16
citations