English
Related papers

Related papers: Compiling Activation Steering into Weights via Nul…

200 papers

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

Cryptography and Security · Computer Science 2024-04-02 Hai Huang , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Computation and Language · Computer Science 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Cryptography and Security · Computer Science 2026-05-21 Junxi Chen , Junhao Dong , Xiaohua Xie

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Machine Learning · Computer Science 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

Cryptography and Security · Computer Science 2026-04-17 Zhengxian Wu , Juan Wen , Wanli Peng , Haowei Chang , Yinghan Zhou , Yiming Xue

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage. Recent…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xingyu Zhu , Beier Zhu , Shuo Wang , Junfeng Fang , Kesen Zhao , Hanwang Zhang , Xiangnan He

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental…

Machine Learning · Computer Science 2026-05-05 Haonan Zhang , Dongxia Wang , Yi Liu , Kexin Chen , Wenhai Wang

Language models (LMs) have been shown to behave unexpectedly post-deployment. For example, new jailbreaks continually arise, allowing model misuse, despite extensive red-teaming and adversarial training from developers. Given most model…

Computation and Language · Computer Science 2024-06-25 Asa Cooper Stickland , Alexander Lyzhov , Jacob Pfau , Salsabila Mahdi , Samuel R. Bowman

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-resource languages (HRLs) like English. Existing solutions, such…

Machine Learning · Computer Science 2026-02-27 Jiaming Liang , Zhaoxin Wang , Handing Wang

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…

Computation and Language · Computer Science 2024-06-14 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Yongbin Li

Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model…

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Cryptography and Security · Computer Science 2025-11-04 Nathalie Kirch , Constantin Weisser , Severin Field , Helen Yannakoudakis , Stephen Casper

Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing…

Computation and Language · Computer Science 2025-01-29 Yue Huang , Jingyu Tang , Dongping Chen , Bingda Tang , Yao Wan , Lichao Sun , Philip S. Yu , Xiangliang Zhang

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

Computation and Language · Computer Science 2026-04-21 San Kim , Gary Geunbae Lee

To ensure AI safety, instruction-tuned Large Language Models (LLMs) are specifically trained to ensure alignment, which refers to making models behave in accordance with human intentions. While these models have demonstrated commendable…

Cryptography and Security · Computer Science 2024-08-19 Haoran Wang , Kai Shu
‹ Prev 1 4 5 6 7 8 10 Next ›