English
Related papers

Related papers: LLM-VA: Resolving the Jailbreak-Overrefusal Trade-…

200 papers

The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings. Without a principled objective for gradient-based optimization,…

Cryptography and Security · Computer Science 2025-11-07 Anamika Lochab , Lu Yan , Patrick Pynadath , Xiangyu Zhang , Ruqi Zhang

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng

Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater vulnerability than their text-only LLM backbones. To…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Xiaohan Zou , Jian Kang , George Kesidis , Lu Lin

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Cryptography and Security · Computer Science 2026-04-06 John T. Halloran

Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…

Machine Learning · Computer Science 2025-09-22 Maithili Joshi , Palash Nandi , Tanmoy Chakraborty

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Computation and Language · Computer Science 2026-02-03 Yuxuan Lu , Yongkang Guo , Yuqing Kong

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Despite the rapid development of safety alignment techniques for LLMs, defending against multi-turn jailbreaks is still a challenging task. In this paper, we conduct a comprehensive comparison, revealing that some existing defense methods…

Cryptography and Security · Computer Science 2025-12-29 Xiaoya Lu , Dongrui Liu , Yi Yu , Luxin Xu , Jing Shao

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Zhihua Wei , Qiang Li , Jian Ruan , Zhenxin Qin , Leilei Wen , Dongrui Liu , Wen Shen

While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such…

Cryptography and Security · Computer Science 2025-01-03 Miao Yu , Junfeng Fang , Yingjie Zhou , Xing Fan , Kun Wang , Shirui Pan , Qingsong Wen

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

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

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Jiaheng Liu , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Yu Wang , Xiaofei Zhou , Yichen Wang , Geyuan Zhang , Tianxing He

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Computation and Language · Computer Science 2025-06-24 Yilei Jiang , Xinyan Gao , Tianshuo Peng , Yingshui Tan , Xiaoyong Zhu , Bo Zheng , Xiangyu Yue

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…

Computation and Language · Computer Science 2026-05-05 Jialin Song , Xiaodong Liu , Weiwei Yang , Wuyang Chen , Mingqian Feng , Xuekai Zhu , Jianfeng Gao

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Md Rafi Ur Rashid , MD Sadik Hossain Shanto , Vishnu Asutosh Dasu , Shagufta Mehnaz

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 In Chong Choi , Jiacheng Zhang , Feng Liu , Yiliao Song

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Cryptography and Security · Computer Science 2026-01-01 Yuan Xin , Dingfan Chen , Linyi Yang , Michael Backes , Xiao Zhang

Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed a variety of attack strategies that can successfully bypass the safety mechanisms of VLMs. Among these approaches, jailbreak methods based…

Cryptography and Security · Computer Science 2025-11-12 Yuxuan Zhou , Yuzhao Peng , Yang Bai , Kuofeng Gao , Yihao Zhang , Yechao Zhang , Xun Chen , Tao Yu , Tao Dai , Shu-Tao Xia