most citedAdaptive Deployment of Untrusted LLMs Reduces Distributed Threats

1 citations · 1 across the 5 of their papers we have counts for

collaborators

11 papers

cs.LG2025

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs

Igor Shilov, Alex Cloud, Aryo Pradipta Gema +5

Large Language Models increasingly possess capabilities that carry dual-use risks. While data filtering has emerged as a pretraining-time mitigation, it faces significant challenge…

cs.AI2025

Evaluating Control Protocols for Untrusted AI Agents

Jon Kutasov, Chloe Loughridge, Yuqi Sun +4

As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untruste…

cs.LG2025

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks

Jack Youstra, Mohammed Mahfoud, Yang Yan +3

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs…

cs.AI2025

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Jonathan Kutasov, Yuqi Sun, Paul Colognese +9

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by p…

cs.CL2025

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Runjin Chen, Andy Arditi, Henry Sleight +2

Large language models interact with users through a simulated 'Assistant' persona. While the Assistant is typically trained to be helpful, harmless, and honest, it sometimes deviat…

cs.AI2025

Inverse Scaling in Test-Time Compute

Aryo Pradipta Gema, Alexander Hägele, Runjin Chen +11

We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between tes…