6 papers
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
Saad Hossain, Tom Tseng, Punya Syon Pandey +8
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, be…
Internal Deployment Gaps in AI Regulation
Joe Kwon, Stephen Casper
Frontier AI regulations primarily focus on systems deployed to external users, where deployment is more visible and subject to outside scrutiny. However, high-stakes applications c…
What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
Nathalie Kirch, Constantin Weisser, Severin Field +2
Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly und…
Practical Principles for AI Cost and Compute Accounting
Stephen Casper, Luke Bailey, Tim Schreier
Policymakers increasingly use development cost and compute as proxies for AI capabilities and risks. Recent laws have introduced regulatory requirements for models or developers th…
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…
The AI Agent Index
Stephen Casper, Luke Bailey, Rosco Hunter +12
Leading AI developers and startups are increasingly deploying agentic AI systems that can plan and execute complex tasks with limited human involvement. However, there is currently…