Waymo
University of Chicago
University of Illinois Urbana-Champaign
Dan HendrycksDirector · Center for AI SafetyResearcher↗MM
Researcher
Mantas Mazeika
Center for AI SafetyResearch Scientist
Mazeika is a lead author of HarmBench (automated red-teaming evaluation) and the WMDP benchmark for measuring and unlearning hazardous knowledge, and co-authored work on tamper-resistant safeguards for open-weight LLMs. He is a research scientist at the Center for AI Safety.
Career & education
Current role
Research Scientist
Previously
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations26,328As of Jun 15, '26
citations+9,957Since last snapshot, Aug 25, '25
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
