# Unraveling LLM Jailbreaks Through Safety Knowledge Neurons

arXiv: https://arxiv.org/abs/2509.01631 · HTML: https://mlsanity.com/paper/2509.01631/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 43)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [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)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [Preference Ranking Optimization for Human Alignment](https://mlsanity.com/paper/2306.17492/) (2023)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications](https://mlsanity.com/paper/2402.05162/) (2024)

## Built on by (most cited first, 7 of 7)

- [SafeSeek: Universal Attribution of Safety Circuits in Language Models](https://mlsanity.com/paper/2603.23268/) (2026)
- [ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging](https://mlsanity.com/paper/2601.05560/) (2026)
- [SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security](https://mlsanity.com/paper/2512.04841/) (2025)
- [AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models](https://mlsanity.com/paper/2603.08275/) (2026)
- [Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models](https://mlsanity.com/paper/2605.27997/) (2026)
- [Incomplete Prompt Jailbreaks in Large Language Models](https://mlsanity.com/paper/2607.20473/) (2026)
- [Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks](https://mlsanity.com/paper/2608.02674/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled substances and the propagation of disinformation, a technique known as "Jailbreak." While some studies have achieved defenses against jailbreak attacks by modifying output distributions or detecting harmful content, the exact rationale still remains elusive. In this work, we present a novel neuron-level interpretability method that focuses on the role of safety-related knowledge neurons. Unlike existing approaches, our method projects the model's internal representation into a more consistent and interpretable vocabulary space. We then show that adjusting the activation of safety-related neurons can effectively control the model's behavior with a mean ASR higher than 97%. Building on this insight, we propose SafeTuning, a fine-tuning strategy that reinforces safety-critical neurons to improve model robustness against jailbreaks. SafeTuning consistently reduces attack success rates across multiple LLMs and outperforms all four baseline defenses. These findings offer a new perspective on understanding and defending against jailbreak attacks.