4 papers
Frontier Models Can Take Actions at Low Probabilities
Alex Serrano, Wen Xing, David Lindner +1
Pre-deployment evaluations inspect only a limited sample of model actions. A malicious model seeking to evade oversight could exploit this by randomizing when to "defect": misbehav…
RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
Rohan Gupta, Erik Jenner
Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. Th…
Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability
Artur Zolkowski, Wen Xing, David Lindner +2
Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignme…
Obfuscated Activations Bypass LLM Latent-Space Defenses
Luke Bailey, Alex Serrano, Abhay Sheshadri +7
Recent latent-space monitoring techniques have shown promise as defenses against LLM attacks. These defenses act as scanners that seek to detect harmful activations before they lea…