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

AI & ML interests

AI security & privacy, algorithmic bias, foundations of ML

Recent Activity

montehoover  updated a dataset about 2 hours ago

tomg-group-umd/DynaBench

JonasGeiping  authored a paper about 17 hours ago

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM

jwkirchenbauer  updated a Space 7 days ago

tomg-group-umd/lm-watermarking

View all activity

Team members 29