Sub-chapter
AI Security Team
Making AI safe also requires security — to stop adversaries gaining access to powerful models, individuals training secret loyalties into models, or models exfiltrating themselves. Join us if you're especially interested in the intersection of cybersecurity and AI.
Learn more
AI Security Reading Group 6 weeks
A closed, in-person reading group exploring critical and neglected problems in AI security — threat models and research agendas for safeguarding advanced AI systems.
AI Security Afternoon Once a semester
A half-day event with invited talks from people working on AI security professionally, plus time for students to connect and ask questions.
AI Security Research Sprints Coming soon
Structured sprints for students who want to move from reading about AI security to working on it. More details to be announced.