UCR AI Safety Group

AI & ML interests

AI Safety

Recent Activity

Erfan-Shayegani  authored a paper 8 days ago

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

Erfan-Shayegani  authored a paper 8 days ago

Unfair Alignment: Examining Safety Alignment Across Vision Encoder Layers in Vision-Language Models

Erfan-Shayegani  authored a paper 10 months ago

Cross-Modal Safety Alignment: Is textual unlearning all you need?

View all activity

Team members 1