Group Milestones

By The Numbers

  • 10 PhD Safety Scholars
  • 6 Masters Safety Scholars
  • 50+ Undergraduate Safety Scholars
  • 30 Current AI Safety Fundamentals participants
  • 130+ AI Safety Fundamentals graduates

Involvement and Impact

Research groups with members hosted by WAISI for speaker events:

Google DeepMindMETRCenter for a New American SecurityAnthropic

Research

See our research page for recent research papers published by WAISI members.

Our members work with the following professors:

Learning (robust) representations and generative modeling
Reinforcement learning and autonomous agents
Natural language processing and machine learning
Adversarial machine learning, privacy, and formal methods
Theory and algorithms for deep learning with foundation models
Algorithmic and theoretical foundations of reliable machine learning
Mobile security, adversarial ML, and systems security research
Machine learning, coding theory, and optimization
Fundamentals of data-driven systems and machine learning
Image analysis, computer vision, and ML in biostatistics
Machine learning, statistical inference, and crowdsourcing
LLM evaluations, high dimensional statistics, and deep learning theory