Tom Goldstein's Lab at University of Maryland, College Park

AI & ML interests

AI security & privacy, algorithmic bias, foundations of ML

Recent Activity

kaiyuyue  authored a paper 3 days ago

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

JonasGeiping  authored a paper 29 days ago

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

JonasGeiping  authored a paper 29 days ago

What do we learn from inverting CLIP models?

View all activity

Team members 26