VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
Paper
•
2410.00296
•
Published
•
6
Xuefeng Du
xfdu1
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
upvoted
a
paper
about 2 months ago
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent
Systems
authored
a paper
9 months ago
Feed Two Birds with One Scone: Exploiting Wild Data for Both
Out-of-Distribution Generalization and Detection
Organizations
None yet