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
The paper introduces a method called Addition by Subtraction to strengthen safety alignment in large language models. By gradually removing identified safety‑critical neurons during finetuning and re‑optimizing preferences, the authors reduce the model’s reliance on sparse components that can be targeted by pruning or ablation attacks. Experiments on four models from three vendors show that this approach improves robustness to both white‑box and black‑box jailbreaks, lowers attack success rates by up to 90%, and enhances truthfulness while preserving general capabilities.
By Hamid Dashtbani, Alexandra Dmitrienko
arXiv:2508.09473v2 Announce Type: replace-cross
Abstract: Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, c...
By Birong Pan, Jianhao Chen, Mayi Xu, Qiankun Pi, Yuanyuan Zhu, Ming Zhong, Tieyun Qian
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
By Hao Li, Jingkun An, Zijun Song, Pengyu Zhu, Rui Li, Hao Wang, Wendi Feng, Yesheng Liu, Lijun Li, Jin-Ge Yao, Lei Sha
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
The paper introduces FDCU, a dual‑constrained subspace projection framework designed to improve machine unlearning for large language models. FDCU limits parameter updates with a dual‑masking rule that preserves general knowledge via Fisher Information while preventing the activation of spurious suppressors through the Principle of Minimal Functional Intervention. Experiments show that FDCU achieves state‑of‑the‑art robustness against retraining attacks while maintaining near‑lossless general utility, thereby ensuring durable safety for LLMs.
By Jiaqing Li, Shide Zhou, Zhibo Zhang, Yuxi Li, Tianlong Yu, Kailong Wang