# Compromising Honesty and Harmlessness in Language Models via Deception Attacks

arXiv: https://arxiv.org/abs/2502.08301 · HTML: https://mlsanity.com/paper/2502.08301/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 46 references that are in the map.
- First posted on arXiv 12 Feb 2025.

## Builds on (most cited first, 30 of 39)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Mitigating the Alignment Tax of RLHF](https://mlsanity.com/paper/2309.06256/) (2023)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [Do Large Language Models Latently Perform Multi-Hop Reasoning?](https://mlsanity.com/paper/2402.16837/) (2024)
- [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [Scheming AIs: Will AIs fake alignment during training in order to get power?](https://mlsanity.com/paper/2311.08379/) (2023)
- [Fine-tuning can cripple your foundation model; preserving features may be the solution](https://mlsanity.com/paper/2308.13320/) (2023)
- [Tell me about yourself: LLMs are aware of their learned behaviors](https://mlsanity.com/paper/2501.11120/) (2025)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://mlsanity.com/paper/2407.04694/) (2024)
- [Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation](https://mlsanity.com/paper/2406.20053/) (2024)

## Built on by (most cited first, 17 of 17)

- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Model Organisms for Emergent Misalignment](https://mlsanity.com/paper/2506.11613/) (2025)
- [Convergent Linear Representations of Emergent Misalignment](https://mlsanity.com/paper/2506.11618/) (2025)
- [Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time](https://mlsanity.com/paper/2510.04340/) (2025)
- [Emergent Misalignment is Easy, Narrow Misalignment is Hard](https://mlsanity.com/paper/2602.07852/) (2026)
- [Large Reasoning Models Are Autonomous Jailbreak Agents](https://mlsanity.com/paper/2508.04039/) (2025)
- [Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders](https://mlsanity.com/paper/2505.14536/) (2025)
- [The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind](https://mlsanity.com/paper/2509.20393/) (2025)
- [LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions](https://mlsanity.com/paper/2510.08211/) (2025)
- [Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment](https://mlsanity.com/paper/2602.14777/) (2026)
- [Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment](https://mlsanity.com/paper/2508.20015/) (2025)
- [Surgical Repair of Insecure Code Generation in LLMs](https://mlsanity.com/paper/2604.16697/) (2026)
- [Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating](https://mlsanity.com/paper/2606.09068/) (2026)
- [Semantic Containment as a Fundamental Property of Emergent Misalignment](https://mlsanity.com/paper/2603.04407/) (2026)
- ["Dark Triad" Model Organisms of Misalignment: Narrow Fine-Tuning Mirrors Human Antisocial Behavior](https://mlsanity.com/paper/2603.06816/) (2026)
- [Probing the Limits of the Lie Detector Approach to LLM Deception](https://mlsanity.com/paper/2603.10003/) (2026)

## Abstract (arXiv)

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has not been shown to pose a serious risk to users. Additionally, research on AI alignment has made significant advancements in training models to refuse generating misleading or toxic content. As a result, LLMs generally became honest and harmless. In this study, we introduce "deception attacks" that undermine both of these traits, revealing a vulnerability that, if exploited, could have serious real-world consequences. We introduce fine-tuning methods that cause models to selectively deceive users on targeted topics while remaining accurate on others. Through a series of experiments, we show that such targeted deception is effective even in high-stakes domains or ideologically charged subjects. In addition, we find that deceptive fine-tuning often compromises other safety properties: deceptive models are more likely to produce toxic content, including hate speech and stereotypes. Finally, we assess whether models can deceive consistently in multi-turn dialogues, yielding mixed results. Given that millions of users interact with LLM-based chatbots, voice assistants, agents, and other interfaces where trustworthiness cannot be ensured, securing these models against deception attacks is critical.