English
Related papers

Related papers: Mosaic: Multimodal Jailbreak against Closed-Source…

200 papers

We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-refusal on benign boundary queries, and instruction following under verifiable constraints.…

Cryptography and Security · Computer Science 2026-03-20 Yipu Dou , Wang Yang

Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introduce a novel method that leverages sequential comic-style…

Cryptography and Security · Computer Science 2025-10-20 Deyue Zhang , Dongdong Yang , Junjie Mu , Quancheng Zou , Zonghao Ying , Wenzhuo Xu , Zhao Liu , Xuan Wang , Xiangzheng Zhang

Despite the rapid progress of Vision-Language Models (VLMs), their capabilities are inadequately assessed by existing benchmarks, which are predominantly English-centric, feature simplistic layouts, and support limited tasks. Consequently,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Ketong Chen , Yuhao Chen , Yang Xue

Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elicit biased or malicious outputs. In this paper, we demonstrate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Chenxi Li , Xianggan Liu , Dake Shen , Yaosong Du , Zhibo Yao , Hao Jiang , Linyi Jiang , Chengwei Cao , Jingzhe Zhang , RanYi Peng , Peiling Bai , Xiande Huang

The emergence of Vision-Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to enhance multi-modal machine learning capabilities. However, this progress has also made VLMs…

Artificial Intelligence · Computer Science 2024-12-24 Zaitang Li , Pin-Yu Chen , Tsung-Yi Ho

The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves…

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Yuan Xiong , Ziqi Miao , Lijun Li , Chen Qian , Jie Li , Jing Shao

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Samar Fares , Klea Ziu , Toluwani Aremu , Nikita Durasov , Martin Takáč , Pascal Fua , Ivan Laptev , Karthik Nandakumar

Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary across users, regions,…

Artificial Intelligence · Computer Science 2026-03-18 Jingyu Peng , Hongyu Chen , Jiancheng Dong , Maolin Wang , Wenxi Li , Yuchen Li , Kai Zhang , Xiangyu Zhao

Multimodal Diffusion Large Language Models (MDLLMs) achieve high-concurrency generation through parallel masked decoding, yet the architectures remain prone to multimodal hallucinations. This structural vulnerability stems from an…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Vishal Narnaware , Animesh Gupta , Kevin Zhai , Zhenyi Wang , Mubarak Shah

Vision-Language Models (VLMs) are rapidly replacing unimodal encoders in modern retrieval and recommendation systems. While their capabilities are well-documented, their robustness against adversarial manipulation in competitive ranking…

Computation and Language · Computer Science 2026-01-21 Yixuan Du , Chenxiao Yu , Haoyan Xu , Ziyi Wang , Yue Zhao , Xiyang Hu

Diffusion-based large language models (dLLMs) have emerged as a promising paradigm, utilizing simultaneous denoising to enable global planning and iterative refinement. While these capabilities are particularly advantageous for long-context…

Machine Learning · Computer Science 2026-01-13 Liang Zheng , Bowen Shi , Yitao Hu , Jiawei Zhang , Ruofan Li , Sheng Chen , Wenxin Li , Keqiu Li

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Aharon Azulay , Jan Dubiński , Zhuoyun Li , Atharv Mittal , Yossi Gandelsman

Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a substantial threat to LLM security. Current strategies for…

Cryptography and Security · Computer Science 2024-06-07 Lin Lu , Hai Yan , Zenghui Yuan , Jiawen Shi , Wenqi Wei , Pin-Yu Chen , Pan Zhou

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial…

Cryptography and Security · Computer Science 2024-02-07 Ziyi Yin , Muchao Ye , Tianrong Zhang , Tianyu Du , Jinguo Zhu , Han Liu , Jinghui Chen , Ting Wang , Fenglong Ma

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…

Cryptography and Security · Computer Science 2025-10-27 Xingwei Zhong , Kar Wai Fok , Vrizlynn L. L. Thing

The emergence of Multimodal Large Language Models (MLRMs) has enabled sophisticated visual reasoning capabilities by integrating reinforcement learning and Chain-of-Thought (CoT) supervision. However, while these enhanced reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Bingrui Sima , Linhua Cong , Wenxuan Wang , Kun He

Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and textual modalities…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Jianting Tang , Yubo Wang , Haoyu Cao , Linli Xu

Though powerful tools for analysis and communication, interactive visualizations often fail to support real-time interaction with large datasets with millions or more records. To highlight and filter data, users indicate values or intervals…

Human-Computer Interaction · Computer Science 2025-07-29 Jeffrey Heer , Dominik Moritz , Ron Pechuk

Multimodal Large Language Models (MLLMs) bridge the gap between visual and textual data, enabling a range of advanced applications. However, complex internal interactions among visual elements and their alignment with text can introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Zuopeng Yang , Jiluan Fan , Anli Yan , Erdun Gao , Xin Lin , Tao Li , Kanghua Mo , Changyu Dong