中文
相关论文

相关论文: One Perturbation, Two Failure Modes: Probing VLM S…

200 篇论文

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Ravikumar Balakrishnan , Sanket Mendapara , Ankit Garg

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

密码学与安全 · 计算机科学 2025-07-31 Chetan Pathade

With the remarkable success of Vision-Language Models (VLMs) on multimodal tasks, concerns regarding their deployment efficiency have become increasingly prominent. In particular, the number of tokens consumed during the generation process…

计算机视觉与模式识别 · 计算机科学 2025-11-21 Zhi Luo , Zenghui Yuan , Wenqi Wei , Daizong Liu , Pan Zhou

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…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this…

Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we…

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…

计算机视觉与模式识别 · 计算机科学 2025-01-14 Zhendong Liu , Yuanbi Nie , Yingshui Tan , Jiaheng Liu , Xiangyu Yue , Qiushi Cui , Chongjun Wang , Xiaoyong Zhu , Bo Zheng

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which…

计算机视觉与模式识别 · 计算机科学 2024-09-20 Hao Cheng , Erjia Xiao , Jindong Gu , Le Yang , Jinhao Duan , Jize Zhang , Jiahang Cao , Kaidi Xu , Renjing Xu

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

密码学与安全 · 计算机科学 2026-05-27 Qilin Liao , Anamika Lochab , Ruqi Zhang

Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.…

机器学习 · 计算机科学 2025-10-14 Menglan Chen , Xianghe Pang , Jingjing Dong , WenHao Wang , Yaxin Du , Siheng Chen

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Jiachen Sun , Changsheng Wang , Jiongxiao Wang , Yiwei Zhang , Chaowei Xiao

Vision-Large-Language-Models (Vision-LLMs) are increasingly being integrated into autonomous driving (AD) systems due to their advanced visual-language reasoning capabilities, targeting the perception, prediction, planning, and control…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Nhat Chung , Sensen Gao , Tuan-Anh Vu , Jie Zhang , Aishan Liu , Yun Lin , Jin Song Dong , Qing Guo

Vision Large Language Models (VLLMs) represent a significant advancement in artificial intelligence by integrating image-processing capabilities with textual understanding, thereby enhancing user interactions and expanding application…

计算与语言 · 计算机科学 2025-05-09 Madhur Jindal , Saurabh Deshpande

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…

计算机视觉与模式识别 · 计算机科学 2024-10-31 Youcheng Huang , Fengbin Zhu , Jingkun Tang , Pan Zhou , Wenqiang Lei , Jiancheng Lv , Tat-Seng Chua

Vision Language Models (VLMs) hold great promise for streamlining labour-intensive medical imaging workflows, yet systematic security evaluations in clinical settings remain scarce. We introduce VSF--Med, an end-to-end vulnerability-scoring…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Binesh Sadanandan , Vahid Behzadan

Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in…

计算机视觉与模式识别 · 计算机科学 2025-02-14 Maan Qraitem , Nazia Tasnim , Piotr Teterwak , Kate Saenko , Bryan A. Plummer

Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Trishna Chakraborty , Udita Ghosh , Aldair Ernesto Gongora , Ruben Glatt , Yue Dong , Jiachen Li , Amit K. Roy-Chowdhury , Chengyu Song

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Shiji Zhao , Shukun Xiong , Yao Huang , Yan Jin , Zhenyu Wu , Jiyang Guan , Ranjie Duan , Jialing Tao , Hui Xue , Xingxing Wei

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

计算与语言 · 计算机科学 2026-03-05 Gabriel Downer , Sean Craven , Damian Ruck , Jake Thomas

As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs),…

人工智能 · 计算机科学 2025-06-23 Peiyuan Tang , Haojie Xin , Xiaodong Zhang , Jun Sun , Qin Xia , Zijiang Yang
‹ 上一页 1 2 3 10 下一页 ›