The paper introduces CAM-Steer, a Category‑Adaptive Multi‑category Safety Steering framework that estimates risk for each harm category by comparing hidden states to safe and unsafe prototypes. It then combines safety directions into a single steering vector and applies a rotation whose angle is set by the estimated risks, preserving the hidden‑state norm. Experiments on three LLM backbones and seven harm categories show that CAM‑Steer outperforms baselines in defense success rate, even when multiple harm categories co‑occur, with negligible inference overhead.
By Chenxi Wang, Ruiyang Huang, Li Huang, Yifan Wu
arXiv:2606. 30360v1 Announce Type: new Abstract: The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization.
By Kuangpu Guo, Qingyan Zheng, Jian Liang, Yongcan Yu, Zilei Wang, Ran He, Tieniu Tan
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a
arXiv:2608.30197v1 Announce Type: new
Abstract: Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on beni...
By Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim, YoungBin Kim
arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.
By Vincent Siu, Nicholas Crispino, David Park, Nathan W. Henry, Zhun Wang, Yang Liu, Dawn Song, Chenguang Wang
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
By Jiayi Li, Kun Zhan
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
By Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang
arXiv:2607. 22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech.
By Domenic Rosati, Ali Dadsetan, Hong Huang, Xijie Zeng, Hassan Chowdhry, Subhabrata Majumdar, Hassan Sajjad, Frank Rudzicz
The paper introduces a chance-constrained approach to fine‑tune large language models (LLMs) that limits the proportion of safety examples whose performance degrades beyond a set threshold relative to a reference model. By replacing the discontinuous violation indicator with a differentiable majorization, the authors derive a tractable, conservative constraint and a closed‑form, constraint‑aware gradient update that focuses on examples near or above the degradation threshold. Experiments on harmful fine‑tuning across three tasks and models show that this tail‑aware method consistently outperforms existing safety‑preserving baselines, suggesting that safety preservation should be treated as a reliability‑constrained optimization problem rather than average‑risk regularization.
By Taha Entesari, Mahyar Fazlyab
arXiv:2609.16305v1 Announce Type: new
Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and...
By Sadia Asif, Mohammad Mohammadi Amiri, Momin Abbas, Tejaswini Pedapati, Prasanna Sattigeri
arXiv:2609.38291v1 Announce Type: cross
Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtim...
By Zhuo Liu, Moxin Li, Zhixin Ma, Wentao Shi, Wenjie Wang, Fuli Feng
arXiv:2604. 08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.
By Niklas Herbster, Martin Zborowski, Alberto Tosato, Gauthier Gidel, Tommaso Tosato