InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Paper
• 2403.02691 • Published
• 1
Zhixiang Liang
ZhixiangLiang
·
AI & ML interests
None yet
Recent Activity
upvoted a collection 16 days ago
Qwen3 authored
a paper
22 days ago
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated
Large Language Model Agents authored
a paper
22 days ago
Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling Organizations
None yet