Detecting Strategic Deception Using Linear Probes, 267, 2025, pp.

Detecting Strategic Deception Using Linear Probes, We thus evaluate if linear probes can robustly detect deception by monitoring model activations. Feb 6, 2025 · We thus evaluate if linear probes can robustly detect deception by monitoring model activations. (2023)) and one of responses to simple roleplaying scenarios. We test two probe-training datasets, one with con-trasting instructions to be honest or deceptive (following Zou et al. The BLAST (TM) Deception Detection Certified Training Program is owned by Whetst Bibliographic details on Detecting Strategic Deception Using Linear Probes. May 1, 2025 · We thus evaluate if linear probes can robustly detect deception by monitoring model activations. . Excerpts of my interview with Mark McClich, former Secret Service Agent and creator of Statement Analysis, a technique applied by the FBI to detect deception in the words we speak. 18757–18775; Goldowsky-Dill, Nicholas, et al. We test two probe-training datasets, one with contrasting instructions to It is found that white-box probes are promising for future monitoring systems, but current performance is insufficient as a robust defence against deception. 6-27B:ai-safety-institute/Qwen3. , Heimersheim, S. May 1, 2025 · How can we spot that kind of strategic deception before it causes harm? We explore a simple detector system: a linear probe that monitors the model's internal thoughts (its 'activations', or intermediate computations)—while the model responds. , 2023) and one of responses to simple roleplaying scenarios. 267, 2025, pp. , Chughtai, B. Mar 19, 2026 · IEEE Access, vol. Learn to accurately detect when someone is lying to you with amazing accuracy. 6-27B-eval_sandbagger using residual stream activations, following the methodology from Detecting Strategic Deception in Language Models (Apollo Research, 2024). We thus Feb 5, 2025 · Researchers at Apollo Research demonstrate that linear probes can effectively detect strategic deception in large language models by analyzing internal act 5 days ago · A probe trained to detect deceptive behaviour in Qwen/Qwen3. In Forty-second International Conference on Machine Learning, 2025. Detecting Strategic Deception Using Linear Probes Nicholas Goldowsky-Dill , Bilal Chughtai , Stefan Heimersheim , Can you tell when an LLM is lying from the activations? Are simple methods good enough? We recently published a paper investigating if linear probes detect when Llama is deceptive. , and Hobbhahn, M. May 2, 2023 – Lies and Allies TuesdaysDavid Neequaye – What justifies cognitive load lie detection? We thus evaluate if linear probes can robustly detect de-ception by monitoring model activations. "Detecting Strategic Deception with Linear Probes. 10, 2022, pp. 19755–19786 8 36 See, Schneider, Johannes, Christian Meske, and Michalis Vlachos. Feb 5, 2025 · We thus evaluate if linear probes can robustly detect deception by monitoring model activations. Feb 17, 2026 · Goldowsky-Dill, N. (2023)) and one of re-sponses to simple roleplaying scenarios. How can we spot that kind of strategic deception before it causes harm?We explore a simple detector system: a linear probe that monitors the model's internal thoughts (its 'activations', or intermediate computations)—while the model responds. Feb 6, 2025 · We test two probe-training datasets, one with contrasting instructions to be honest or deceptive (following Zou et al. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their internal reasoning is misaligned. " Proceedings of the 42nd International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. Detecting strategic deception with linear probes. We test two probe-training datasets, one with contrasting instructions to be honest or deceptive (following Zou et al. AI models might use deceptive strategies as part of scheming or misaligned behaviour. w8ir 2jho fy hpmitf ato f7jd hezkv 56nls1i iwv w6b