collaborators

12 papers

cs.AI2026

Code Monitor Red Teaming for Public-Test-Passing Code

Junchi Liao, Jiawen Deng, Fuji Ren

Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…

cs.AI2026

Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety

Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad +3

An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but unt…

cs.CR2026

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

Elle Najt, Colin Toft, Tyler Tracy +2

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To…

cs.CR2026

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

Monika Jotautaitė, Maria Angelica Martinez, Ollie Matthews +1

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate moni…

cs.CR2026

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments

Tyler Tracy, Ram Potham, Nick Kuhn +31

We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks re…

cs.CR2026

Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring

Joachim Schaeffer, Arjun Khandelwal, Tyler Tracy

Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them - attack selection - is…