Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing

• URL: http://arxiv.org/abs/2606.17478v1
• Date: Tue, 16 Jun 2026 03:41:29 GMT
• Title: Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
• Abstract summary: We introduce STATEWITNESS, an activation explainer for deception auditing.<n>A separate decoder reads a target model's hidden states, then answers natural-language queries or emits structured reports about them.<n>We evaluate STATEWITNESS on two target reasoning LLMs across seven deception datasets.
• Score: 22.30404793367838
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors either score visible transcripts or derive scalar probe scores from representation vectors, leaving little inspectable evidence about why a response is suspicious. We introduce STATEWITNESS, an activation explainer for deception auditing. A separate decoder reads a target model's hidden states, then answers natural-language queries or emits structured reports about them. We evaluate STATEWITNESS on two target reasoning LLMs across seven deception datasets. STATEWITNESS reaches 0.916 mean AUROC, a relative gain of 11.6% over the best black-box text monitor and 25.0% over the best activation-probe baseline under the same evaluation protocol. When combined with existing monitors, STATEWITNESS reduces missed deceptive examples in simple threshold ensembles. Beyond scalar detection, the decoder returns query-level answers, schema reports, and token- or sentence-level evidence traces for human inspection. We view this interface as a potential building block for broader interpretability and alignment tools.

Related papers

• The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics [0.0]
  Large language models are increasingly used in blockchain forensic investigations.<n> adversarial deception reduces drain detection by 20.0 percentage points.<n>Models correctly describe the hidden drain mechanism but accept the contract's framing and dismiss it as benign.
  arXiv  Detail & Related papers  (2026-09-12T18:45:24Z)
• LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger [11.70343232168598]
  LedgerMind is a provenance-constrained agentic reasoning engine.<n>It targets four recurring failure patterns that final-answer accuracy tends to obscure.<n>It improves both answer accuracy and trajectory-level faithfulness.
  arXiv  Detail & Related papers  (2026-07-30T15:35:34Z)
• Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries [14.42294978688412]
  We present Veritas, a semantically grounded framework for binary memory corruption vulnerability detection.<n>Veritas combines a static slicer over RetDec-lifted LLVM IR, a dual-view LLM detector, and a multi-agent validator.<n>We implement Veritas as a modular pipeline and evaluate it on a curated benchmark of real-world binary vulnerability cases.
  arXiv  Detail & Related papers  (2026-05-14T17:16:11Z)
• Logic-Regularized Verifier Elicits Reasoning from LLMs [63.65875399266337]
  We propose LOVER, an unsupervised verifier regularized by logical rules.<n>Lover treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints.<n>Lover significantly outperforms unsupervised baselines.
  arXiv  Detail & Related papers  (2026-05-07T09:03:49Z)
• From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks [49.57538588967748]
  Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks.<n>We uncover a consistent phenomenon across modern architectures, including LLaMA, Qwen, and Gemma.<n>We show that symbolic reasoning failures in LLMs are not due to missing representations or insufficient scale, but arise from structured interference within the model's computation graph.
  arXiv  Detail & Related papers  (2026-04-01T11:40:12Z)
• AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing [9.271196825503417]
  Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound.<n>We present AEGIS, a novel multi-agent framework that shifts detection from ungrounded speculation to forensic verification over a closed factual substrate.<n>It reduces the false positive rate by up to 54.40% compared to leading baselines, at an average cost of $0.09 per sample without any task-specific training.
  arXiv  Detail & Related papers  (2026-03-21T04:12:04Z)
• DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents [0.0]
  We introduce DECEPTGUARD, a unified framework that systematically compares three monitoring regimes.<n>We introduce DECEPTSYNTH, a scalable synthetic pipeline for generating deception-positive and deception-negative agent trajectories.<n>Our monitors are optimized on 4,800 synthetic trajectories and evaluated on 9,200 held-out samples from DeceptArena.
  arXiv  Detail & Related papers  (2026-03-14T06:45:43Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers [59.168391398830515]
  We evaluate 12 pre-trained LLMs and one specialized fact-verifier, using a collection of examples from 14 fact-checking benchmarks.<n>We highlight the importance of addressing annotation errors and ambiguity in datasets.<n> frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance.
  arXiv  Detail & Related papers  (2025-06-16T10:32:10Z)
• From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring [12.505882642773829]
  Existing moderators mainly practice a conventional full detection, which determines the harmfulness based on the complete LLM output.<n>Recent works pay more attention to partial detection where moderators oversee the generation midway and early stop the output if harmfulness is detected.<n>We propose the streaming content monitor, which is trained with dual supervision of response- and token-level labels.
  arXiv  Detail & Related papers  (2025-06-11T17:59:58Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.