Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Paper
•
2505.21494
•
Published
•
8
•
2
jiaxiaojunQAQ
jiaxiaojunQAQ
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Diffusion Language Models are Super Data Learners
upvoted
a
paper
2 months ago
Imperceptible Jailbreaking against Large Language Models
upvoted
a
paper
2 months ago
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
Organizations
commented
a
paper
6 months ago