Difficulties with Evaluating a Deception Detector for AIs

• URL: http://arxiv.org/abs/2511.22662v1
• Date: Thu, 27 Nov 2025 17:53:46 GMT
• Title: Difficulties with Evaluating a Deception Detector for AIs
• Abstract summary: Building reliable deception detectors for AI systems would be valuable in mitigating risks from advanced AI systems.<n>But evaluating the reliability and efficacy of a proposed deception detector requires examples that we can confidently label as either deceptive or honest.<n>We argue that we currently lack the necessary examples and further identify several concrete obstacles in collecting them.
• Score: 11.600884786394316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced AI systems. But evaluating the reliability and efficacy of a proposed deception detector requires examples that we can confidently label as either deceptive or honest. We argue that we currently lack the necessary examples and further identify several concrete obstacles in collecting them. We provide evidence from conceptual arguments, analysis of existing empirical works, and analysis of novel illustrative case studies. We also discuss the potential of several proposed empirical workarounds to these problems and argue that while they seem valuable, they also seem insufficient alone. Progress on deception detection likely requires further consideration of these problems.

Related papers

• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• The AI Cognitive Trojan Horse: How Large Language Models May Bypass Human Epistemic Vigilance [0.0]
  Large language model (LLM)-based conversational AI systems present a challenge to human cognition.<n>This paper proposes that a significant epistemic risk from conversational AI may lie not in inaccuracy or intentional deception, but in something more fundamental.
  arXiv  Detail & Related papers  (2026-01-11T22:28:56Z)
• AI Deception: Risks, Dynamics, and Controls [149.20033748212012]
  This project provides a comprehensive and up-to-date overview of the AI deception field.<n>We identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception.<n>We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment.
  arXiv  Detail & Related papers  (2025-11-27T16:56:04Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Deep Learning Models for Robust Facial Liveness Detection [56.08694048252482]
  This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques.<n>By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision.
  arXiv  Detail & Related papers  (2025-08-12T17:19:20Z)
• Causality can systematically address the monsters under the bench(marks) [64.36592889550431]
  Benchmarks are plagued by various biases, artifacts, or leakage.<n>Models may behave unreliably due to poorly explored failure modes.<n> causality offers an ideal framework to systematically address these challenges.
  arXiv  Detail & Related papers  (2025-02-07T17:01:37Z)
• A Survey and Evaluation of Adversarial Attacks for Object Detection [11.48212060875543]
  Deep learning models are vulnerable to adversarial examples that can deceive them into making confident but incorrect predictions.<n>This vulnerability pose significant risks in high-stakes applications such as autonomous vehicles, security surveillance, and safety-critical inspection systems.<n>This paper presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures.
  arXiv  Detail & Related papers  (2024-08-04T05:22:08Z)
• Evaluating AI Evaluation: Perils and Prospects [8.086002368038658]
  This paper contends that the prevalent evaluation methods for these systems are fundamentally inadequate. I argue that a reformation is required in the way we evaluate AI systems and that we should look towards cognitive sciences for inspiration.
  arXiv  Detail & Related papers  (2024-07-12T12:37:13Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• Unfooling Perturbation-Based Post Hoc Explainers [12.599362066650842]
  Recent work demonstrates that perturbation-based post hoc explainers can be fooled adversarially. This discovery has adverse implications for auditors, regulators, and other sentinels. In this work, we rigorously formalize this problem and devise a defense against adversarial attacks on perturbation-based explainers.
  arXiv  Detail & Related papers  (2022-05-29T21:28:12Z)
• Adversarial Example Detection for DNN Models: A Review [13.131592630524905]
  The aim of adversarial example (AE) is to fool the Deep Learning model which makes it a potential risk for DL applications. Few reviews and surveys were published and theoretically showed the taxonomy of the threats and the countermeasure methods. A detailed discussion for such methods is provided and experimental results for eight state-of-the-art detectors are presented.
  arXiv  Detail & Related papers  (2021-05-01T09:55:17Z)
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis [71.57324258813674]
  This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model against different unsafe inputs. Experimental results show that the proposed approach is effective in detecting both powerful adversarial examples and out-of-distribution inputs.
  arXiv  Detail & Related papers  (2021-01-28T16:38:26Z)

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.