collaborators

8 papers

cs.CR2026

Evading Chain-of-Thought Monitoring Through Model Poisoning

Giorgio Severi, Shujaat Mirza, Blake Bullwinkel +1

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 ac…

cs.CL2026

Learning to Attack and Defend: Adaptive Red Teaming of Language Models via GRPO

Blake Bullwinkel, Eugenia Kim, Amanda Minnich +1

AI red teaming must continually adapt to evolving attackers and defenders. Reinforcement learning offers a promising approach to discovering novel attacks, and co-training methods…

cs.CL2026

XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

Dasol Choi, Eugenia Kim, Jaewon Noh +14

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's a…

cs.CR2026

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Blake Bullwinkel, Giorgio Severi, Keegan Hines +3

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in…

cs.CR2025

A Systematization of Security Vulnerabilities in Computer Use Agents

Daniel Jones, Giorgio Severi, Martin Pouliot +7

Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise enviro…

cs.CR2025

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks

Blake Bullwinkel, Mark Russinovich, Ahmed Salem +8

Recent research has demonstrated that state-of-the-art LLMs and defenses remain susceptible to multi-turn jailbreak attacks. These attacks require only closed-box model access and…