Talks
Slides from selected invited talks and workshops. Reach out if you would like a longer version or the source files.
AI Safety Workshop: Alignment, Oversight and Deception
ADIA Lab & UGR Summer School 2026 — Responsible AI in the Generative and Agentic AI Era
A workshop on AI safety for the generative and agentic era, covering how we specify what models should do (alignment), how we verify they actually do it (oversight), and how deceptive behavior can emerge and be detected in increasingly capable systems.
Adaptively Robust and Forgery-Resistant Watermarking
Invited talk to the watermarking team at Meta (FAIR), hosted by Hady Elsahar.
An overview of recent work on content watermarks for language and image models that hold up under adaptive attacks and resist forgery, including takeaways from our ICML'25 spotlight on adaptive attacks against LLM watermarks.