mlsanityData to 7 Oct 2026

AI Deception: A Survey of Examples, Risks, and Potential Solutions

arXiv 2308.14752 ↗First posted 28 Aug 2023cs.CY cs.AI cs.HCcited by 185

Not on the map. Why?

Cited by 31 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical examples of AI deception, discussing both special-use AI systems (including Meta's CICERO) built for specific competitive situations, and general-purpose AI systems (such as large language models). Next, we detail several risks from AI deception, such as fraud, election tampering, and losing control of AI systems. Finally, we outline several potential solutions to the problems posed by AI deception: first, regulatory frameworks should subject AI systems that are capable of deception to robust risk-assessment requirements; second, policymakers should implement bot-or-not laws; and finally, policymakers should prioritize the funding of relevant research, including tools to detect AI deception and to make AI systems less deceptive. Policymakers, researchers, and the broader public should work proactively to prevent AI deception from destabilizing the shared foundations of our society.

Key facts. Cited by 185 papers in the map (data through 7 Oct 2026). Builds on 40 of its 127 references that are in the map. First posted on arXiv 28 Aug 2023.

Builds on

40 of 127 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  8. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  9. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  10. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  11. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  12. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 805
28 more
  1. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  2. 2020Aligning AI With Shared Human Valuescited by 706
  3. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  4. 2023A Watermark for Large Language Modelscited by 667
  5. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  6. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  7. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  8. 2023Role-Play with Large Language Modelscited by 290
  9. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 211
  10. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  11. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 174
  12. 2023Model evaluation for extreme riskscited by 167
  13. 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 157
  14. 2021Goal Misgeneralization in Deep Reinforcement Learningcited by 122
  15. 2022Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goalscited by 120
  16. 2023Explore, Establish, Exploit: Red Teaming Language Models from Scratchcited by 111
  17. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  18. 2023Deception Abilities Emerged in Large Language Modelscited by 99
  19. 2018The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communitiescited by 78
  20. 2023Overthinking the Truth: Understanding how Language Models Process False Demonstrationscited by 78
  21. 2023Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblockscited by 77
  22. 2023Spear Phishing With Large Language Modelscited by 49
  23. 2023Evaluating Superhuman Models with Consistency Checkscited by 47
  24. 2023Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Modelscited by 46
  25. 2023Characterizing Manipulation from AI Systemscited by 43
  26. 2023Can large language models democratize access to dual-use biotechnology?cited by 33
  27. 2023Artificial Influence: An Analysis Of AI-Driven Persuasioncited by 31
  28. 2023Playing the Werewolf game with artificial intelligence for language understandingcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 53; 2025: 58; 2026: 60.

185 papers.

Sort:

By area:

  1. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  2. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  3. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 478
  4. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 415
  5. 2024PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preferencecited by 252
  6. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  7. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 164
  8. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 154
  9. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 132
  10. 2024AI Sandbagging: Language Models can Strategically Underperform on Evaluationscited by 131
  11. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 123
  12. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 107
38 more
  1. 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 102
  2. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
  3. 2023How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questionscited by 82
  4. 2024Truth is Universal: Robust Detection of Lies in LLMscited by 78
  5. 2023Alignment for Honestycited by 72
  6. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 66
  7. 2025The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systemscited by 57
  8. 2024Determinants of LLM-assisted Decision-Makingcited by 55
  9. 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 55
  10. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  11. 2024The Geometry of Concepts: Sparse Autoencoder Feature Structurecited by 52
  12. 2023Managing extreme AI risks amid rapid progresscited by 48
  13. 2024Thousands of AI Authors on the Future of AIcited by 48
  14. 2025Large Language Models Pass the Turing Testcited by 48
  15. 2024People cannot distinguish GPT-4 from a human in a Turing testcited by 46
  16. 2024On Targeted Manipulation and Deception when Optimizing LLMs for User Feedbackcited by 45
  17. 2023Welfare Diplomacy: Benchmarking Language Model Cooperationcited by 43
  18. 2024Stress-Testing Capability Elicitation With Password-Locked Modelscited by 42
  19. 2024Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Samplingcited by 33
  20. 2024Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistantcited by 32
  21. 2024Adversaries Can Misuse Combinations of Safe Modelscited by 31
  22. 2023Challenges with unsupervised LLM knowledge discoverycited by 30
  23. 2024Standards for Belief Representations in LLMscited by 30
  24. 2025Evaluating Frontier Models for Stealth and Situational Awarenesscited by 30
  25. 2023Provably safe systems: the only path to controllable AGIcited by 29
  26. 2024Steering Language Models with Game-Theoretic Solverscited by 28
  27. 2024From Lived Experience to Insight: Unpacking the Psychological Risks of Using AI Conversational Agentscited by 25
  28. 2025Mitigating Deceptive Alignment via Self-Monitoringcited by 25
  29. 2023Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournamentcited by 24
  30. 2024The Shutdown Problem: An AI Engineering Puzzle for Decision Theoristscited by 22
  31. 2024Noise Injection Reveals Hidden Capabilities of Sandbagging Language Modelscited by 22
  32. 2024AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracycited by 21
  33. 2024Language Models in Dialogue: Conversational Maxims for Human-AI Interactionscited by 21
  34. 2025The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Processcited by 21
  35. 2024BeHonest: Benchmarking Honesty in Large Language Modelscited by 20
  36. 2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Reviewcited by 19
  37. 2024Implicit Personalization in Language Models: A Systematic Studycited by 18
  38. 2024When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedbackcited by 17

50 most cited of 185 All 185 (JSON)