Snowcat
Panminghui
·
AI & ML interests
LLM Safety
DCAI
Recent Activity
upvoted a paper about 1 month ago
Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents liked a dataset about 1 month ago
CHATS-Lab/MT-AgentRisk upvoted a paper 3 months ago
Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents