PyRIT: Democratizing AI Red Teaming Through Open-Source Tooling
Roman Lutz, Eugenia Kim, Richard Lundeen et al.
· 0 citations
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Preprint
Aug 2026
Evading Chain-of-Thought Monitoring Through Model Poisoning
Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoors can be implanted in...
Giorgio Severi, Shujaat Mirza, Blake Bullwinkel et al.
· 0 citations