English
Related papers

Related papers: Compiling Activation Steering into Weights via Nul…

200 papers

In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…

Computation and Language · Computer Science 2024-10-15 Yifan Luo , Zhennan Zhou , Meitan Wang , Bin Dong

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…

Computation and Language · Computer Science 2026-02-09 Himanshu Singh , Ziwei Xu , A. V. Subramanyam , Mohan Kankanhalli

Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts often overlook attacks that exploit the model's capacity for…

Computation and Language · Computer Science 2025-12-01 Zhaoxin Zhang , Borui Chen , Yiming Hu , Youyang Qu , Tianqing Zhu , Longxiang Gao

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Computation and Language · Computer Science 2026-03-10 Guoli Wang , Haonan Shi , Tu Ouyang , An Wang

Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the context of LLMs deployed as Web Services, which typically…

Computation and Language · Computer Science 2025-02-13 Wenjie Mo , Jiashu Xu , Qin Liu , Jiongxiao Wang , Jun Yan , Hadi Askari , Chaowei Xiao , Muhao Chen

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-17 Amirbek Djanibekov , Nurdaulet Mukhituly , Kentaro Inui , Hanan Aldarmaki , Nils Lukas

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

Computation and Language · Computer Science 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Cryptography and Security · Computer Science 2025-11-19 Hajun Kim , Hyunsik Na , Daeseon Choi

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

Cryptography and Security · Computer Science 2025-05-29 Yao Huang , Yitong Sun , Shouwei Ruan , Yichi Zhang , Yinpeng Dong , Xingxing Wei

Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic…

Computation and Language · Computer Science 2025-05-28 Wenbo Pan , Zhichao Liu , Qiguang Chen , Xiangyang Zhou , Haining Yu , Xiaohua Jia

Alignment of Large Language Models (LLMs) is the ability to satisfy desired objectives during generation, which is critical for trustworthy deployment. In practice, alignment is often operationalized through multiple objectives such as…

Computation and Language · Computer Science 2026-05-19 Gautam Siddharth Kashyap , Mark Dras , Usman Naseem

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Computation and Language · Computer Science 2024-07-08 Xinglin Li , Xianwen He , Yao Li , Minhao Cheng

Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…

Cryptography and Security · Computer Science 2024-10-08 Yiting Dong , Guobin Shen , Dongcheng Zhao , Xiang He , Yi Zeng

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…

Artificial Intelligence · Computer Science 2024-06-17 Wei Zhao , Zhe Li , Yige Li , Ye Zhang , Jun Sun

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Cryptography and Security · Computer Science 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Machine Learning · Computer Science 2025-01-07 Ziwei Zheng , Junyao Zhao , Le Yang , Lijun He , Fan Li

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

Computation and Language · Computer Science 2025-12-23 Xiang Li , Chong Zhang , Jia Wang , Fangyu Wu , Yushi Li , Xiaobo Jin

Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data or with low-rank adaptation, pre-trained safety behaviors are…

Artificial Intelligence · Computer Science 2025-10-28 Bingjie Zhang , Yibo Yang , Zhe Ren , Dandan Guo , Jindong Gu , Philip Torr , Bernard Ghanem

Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank…

Computation and Language · Computer Science 2026-02-09 Jiayi Tian , Ryan Solgi , Jinming Lu , Yifan Yang , Hai Li , Zheng Zhang