arXiv AI August 28, 2026 By Zhiyuan Xu, Muhammad Firhard Roslan, Joseph Gardiner, Sana Belguith, Lichao Wu

NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation

NeuronFuzz is a white‑box fuzzing framework that uses internal safety neurons of large language models as continuous feedback for safety evaluation, eliminating the need to generate full model responses during testing. It constructs a SafetyOracle that converts neuron activations into a differentiable safety alarm score, enabling gradient‑based identification of sensitive template positions and fluent, context‑compatible prompt mutations. Evaluated on 21 text and multimodal models, NeuronFuzz achieves a 76‑100% jailbreak discovery rate on five white‑box source models and demonstrates strong zero‑shot transfer to open‑weight and proprietary targets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 26

NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation

Safety evaluation is critical for assessing whether aligned Large Language Models (LLMs) remain robust against jailbreak attacks. Existing automated testing methods, however, largely rely on response-...

llms multimodal safety

arXiv Machine Learning

Jun 15

NeST: Neuron Selective Tuning for LLM Safety

arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).

By Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi

llms fine-tuning multimodal safety

arXiv Machine Learning

Jun 25

RAS: Measuring LLM Safety Through Refusal Alignment

arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.

By Chang-Chieh Huang, Yan-Lun Chen, Chia-Mu Yu, Wei-Bin Lee

llms safety

arXiv AI

Jun 3

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense

arXiv:2606. 03486v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffixes, and multi-turn buildup.

By Zhongyang Lin, Ziran Zhao, Feifei Zhai, Pengyuan Liu

llms multimodal safety

arXiv AI

Aug 11

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

arXiv:2509. 03985v2 Announce Type: replace-cross Abstract: In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs.

By Chuhan Zhang, Ye Zhang, Bowen Shi, Yuyou Gan, Tianyu Du, Shouling Ji, Dazhan Deng, Yingcai Wu

llms safety

arXiv AI

Jul 20

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.

By Wenpeng Xing, Bohan Yang, Mohan Li, Chunqiang Hu, Haitao Xu, Ningyu Zhang, Bo Lin, Meng Han

llms multimodal benchmarks safety

One email a morning, machine-written

Related stories

NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation

NeST: Neuron Selective Tuning for LLM Safety

RAS: Measuring LLM Safety Through Refusal Alignment

NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs