Hugging Face Trending Papers

NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation

arXiv AI
Aug 28

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.

By Zhiyuan Xu, Muhammad Firhard Roslan, Joseph Gardiner, Sana Belguith, Lichao Wu
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
arXiv AI
Jul 23

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

arXiv:2607. 19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates.

By Qingjia Huang, Jingyu Zhang, Jianguo Wu, Yakai Li, Weijuan Zhang, Yankai Rong, Junyi Yao, Shengzhi Zhang, Xiaoqi Jia
Hugging Face Trending Papers
Jul 2

Safety Targeted Embedding Exploit via Refinement

Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.

arXiv AI
Aug 26

NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution

NeuronGuard is a fine‑tuning defense for large language models that hardens them against both jailbreak and neuron‑level attacks. It redistributes safety signals across many neurons by identifying safety‑critical ones with per‑layer linear classifiers, enforcing refusal behavior when those neurons are ablated, and applying KL‑divergence regularization for consistency. A randomized gradient projection preserves task performance, and the authors provide a formal guarantee that NeuronGuard lowers the attack success rate upper bound, with experiments showing near‑zero success rates across multiple models and attack strategies.

By Anjun Gao, Yueyang Quan, Yufei Xia, Zhuqing Liu, Minghong Fang