VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
Paper
•
2410.00296
•
Published
•
4
•
2
Reshmi Ghosh
reshmighosh
·
AI & ML interests
LLM, Responsible AI, NLP, HCI
Organizations
reshmighosh's activity
commented
a
paper
about 1 month ago