arXiv Machine Learning August 11, 2026 By Yuxiao Li, Gjergji Kasneci

Safety Cost of Steering Vectors Is Separable and Reducible

Read the original on arXiv Machine Learning →

arXiv:2608. 08383v1 Announce Type: cross Abstract: Steering vectors are a lightweight tool for controlling LLM behavior.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 30

On the Vulnerability of Parameter-Level Defenses to Model Merging

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

fine-tuning

arXiv Machine Learning

Jun 5

Steering Vectors are an Adversarial Attack Surface

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

llms fine-tuning multimodal safety

arXiv AI

6d ago

SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives

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

llms benchmarks safety

arXiv Machine Learning

Jul 14

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

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

llms fine-tuning multimodal safety

arXiv AI

Jun 6

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

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

llms reinforcement-learning safety

arXiv Machine Learning

Jul 28

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety

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

fine-tuning safety

Related stories

On the Vulnerability of Parameter-Level Defenses to Model Merging

Steering Vectors are an Adversarial Attack Surface

SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety