SOURCE-LINKED INTELLIGENCE

MOLE: Detecting Insider Threats in AI Agents

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison training data, or weaken release gates. Existing benchmarks do not test whether defenders can detect this activity among routine work under a limited review budget. We introduce MOLE, an open benchmark of 150 AI-operated accounts sharing 9 stateful services over 30 workdays, with 12 threats and 8 corpora from four models totaling roughly 20 billion tokens. Of 39 agent models, 72% complete most assigned harmful objectives and agent refusal does not pr

Read original source ↗ Open in workspace

recordType

paper

region

Global