# LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts

arXiv: https://arxiv.org/abs/2410.10700 · HTML: https://mlsanity.com/paper/2410.10700/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 80 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 30 of 59)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)

## Built on by (most cited first, 30 of 86)

- [X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents](https://mlsanity.com/paper/2504.13203/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking](https://mlsanity.com/paper/2502.12893/) (2025)
- [Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models](https://mlsanity.com/paper/2502.11054/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety](https://mlsanity.com/paper/2503.05021/) (2025)
- [MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation](https://mlsanity.com/paper/2510.15186/) (2025)
- [SaRO: Enhancing LLM Safety through Reasoning-based Alignment](https://mlsanity.com/paper/2504.09420/) (2025)
- [SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks](https://mlsanity.com/paper/2502.11090/) (2025)
- [OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs](https://mlsanity.com/paper/2601.01592/) (2026)
- [MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety](https://mlsanity.com/paper/2602.01539/) (2026)
- [SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning](https://mlsanity.com/paper/2505.16186/) (2025)
- [Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search](https://mlsanity.com/paper/2503.10619/) (2025)
- [SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks](https://mlsanity.com/paper/2602.06854/) (2026)
- [Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning](https://mlsanity.com/paper/2501.19180/) (2025)
- [Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs](https://mlsanity.com/paper/2508.16347/) (2025)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks](https://mlsanity.com/paper/2503.19134/) (2025)
- [Jailbreaking to Jailbreak](https://mlsanity.com/paper/2502.09638/) (2025)
- [Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?](https://mlsanity.com/paper/2505.17650/) (2025)
- [Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning](https://mlsanity.com/paper/2504.01278/) (2025)
- [Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks](https://mlsanity.com/paper/2510.02286/) (2025)
- [Quantifying Trust: Financial Risk Management for Trustworthy AI Agents](https://mlsanity.com/paper/2604.03976/) (2026)
- [MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety](https://mlsanity.com/paper/2605.01687/) (2026)
- [SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues](https://mlsanity.com/paper/2506.00668/) (2025)
- [The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search](https://mlsanity.com/paper/2512.01353/) (2025)
- [Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks](https://mlsanity.com/paper/2604.18660/) (2026)
- [AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research](https://mlsanity.com/paper/2511.04316/) (2025)
- [Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay](https://mlsanity.com/paper/2601.10589/) (2026)
- [ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack](https://mlsanity.com/paper/2601.20903/) (2026)

## Abstract (arXiv)

Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training. In this paper, we identify a new safety vulnerability in LLMs: their susceptibility to textitnatural distribution shifts between attack prompts and original toxic prompts, where seemingly benign prompts, semantically related to harmful content, can bypass safety mechanisms. To explore this issue, we introduce a novel attack method, textitActorBreaker, which identifies actors related to toxic prompts within pre-training distribution to craft multi-turn prompts that gradually lead LLMs to reveal unsafe content. ActorBreaker is grounded in Latour's actor-network theory, encompassing both human and non-human actors to capture a broader range of vulnerabilities. Our experimental results demonstrate that ActorBreaker outperforms existing attack methods in terms of diversity, effectiveness, and efficiency across aligned LLMs. To address this vulnerability, we propose expanding safety training to cover a broader semantic space of toxic content. We thus construct a multi-turn safety dataset using ActorBreaker. Fine-tuning models on our dataset shows significant improvements in robustness, though with some trade-offs in utility. Code is available at https://github.com/AI45Lab/ActorAttack.