ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
Paper
•
2503.22738
•
Published
•
15
Mintong Kang
Cometkmt
AI & ML interests
trustworthy ML
Recent Activity
upvoted
a
paper
14 days ago
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
updated
a dataset
about 1 month ago
AI-Secure/MMDecodingTrust-T2I
updated
a dataset
about 2 months ago
AI-Secure/MMDecodingTrust-T2I
Organizations
