FORTIS: Benchmarking Over-Privilege in Agent Skills
Paper • 2605.09163 • Published • 4
Yue Zhao
yzhao062
AI & ML interests
AI Auditing, AI Agents, AI Evaluation, AI Safety, AI Security
Recent Activity
authored a paper 1 day ago
CatchBench: When Can an Agent Failure Be Caught? authored a paper 1 day ago
GRADE: Graph Representation of LLM Agent Dependency and Execution authored a paper 1 day ago
Auditable AgentsOrganizations
None yet
upvoted a paper 2 days ago