English
Related papers

Related papers: When Think-with-Image Meets Safety: What Determine…

200 papers

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

Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Chongxin Li , Hanzhang Wang , Lian Duan

Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce…

Cryptography and Security · Computer Science 2026-03-25 Chenyu Zhang , Lanjun Wang , Yiwen Ma , Wenhui Li , Yi Tu , An-An Liu

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…

Cryptography and Security · Computer Science 2026-05-12 Yu Chen , Yuanhao Liu , Qi Cao

Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Zeyuan Yang , Xueyang Yu , Delin Chen , Maohao Shen , Chuang Gan

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Cryptography and Security · Computer Science 2023-08-21 Xiangyu Qi , Kaixuan Huang , Ashwinee Panda , Peter Henderson , Mengdi Wang , Prateek Mittal

While humans can flexibly leverage interactive visual cognition for complex problem-solving, enabling Large Vision-Language Models (LVLMs) to learn similarly adaptive behaviors with visual tools remains challenging. A significant hurdle is…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Zhaochen Su , Linjie Li , Mingyang Song , Yunzhuo Hao , Zhengyuan Yang , Jun Zhang , Guanjie Chen , Jiawei Gu , Juntao Li , Xiaoye Qu , Yu Cheng

Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside…

Cryptography and Security · Computer Science 2025-04-23 Yulin Chen , Haoran Li , Yirui Zhang , Zihao Zheng , Yangqiu Song , Bryan Hooi

The "thinking with images" paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of-thought to image-interactive reasoning. By invoking visual tools or generating intermediate…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Chi Zhang , Haibo Qiu , Qiming Zhang , Zhixiong Zeng , Lin Ma , Jing Zhang

Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities…

Computation and Language · Computer Science 2025-07-04 Riccardo Cantini , Nicola Gabriele , Alessio Orsino , Domenico Talia

Text-to-Image(T2I) models typically deploy safety filters to prevent the generation of sensitive images. Unfortunately, recent jailbreaking attack methods manually design instructions for the LLM to generate adversarial prompts, which…

Cryptography and Security · Computer Science 2025-11-24 Chenyu Zhang , Lanjun Wang , Yiwen Ma , Wenhui Li , An-An Liu

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Omar Sharif , Eftekhar Hossain , Patrick Ng

Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization. However, new multimodal fusion models tokenize all input…

Cryptography and Security · Computer Science 2024-10-24 Javier Rando , Hannah Korevaar , Erik Brinkman , Ivan Evtimov , Florian Tramèr

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Artificial Intelligence · Computer Science 2025-11-04 Yifan Xia , Guorui Chen , Wenqian Yu , Zhijiang Li , Philip Torr , Jindong Gu

Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to…

Machine Learning · Computer Science 2026-02-03 Kaiyuan Cui , Yige Li , Yutao Wu , Xingjun Ma , Sarah Erfani , Christopher Leckie , Hanxun Huang

In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs). We conduct a systematic empirical analysis of the harmlessness performance of representative MLLMs and reveal that the image input poses…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Yifan Li , Hangyu Guo , Kun Zhou , Wayne Xin Zhao , Ji-Rong Wen

Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool interactions. However, existing open-source models often exhibit blind tool-use reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Chaoyang Wang , Kaituo Feng , Dongyang Chen , Zhongyu Wang , Zhixun Li , Sicheng Gao , Meng Meng , Xu Zhou , Manyuan Zhang , Yuzhang Shang , Xiangyu Yue

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…

Cryptography and Security · Computer Science 2025-10-14 Aofan Liu , Lulu Tang

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