English
Related papers

Related papers: Internal Activation Revision: Safeguarding Vision …

200 papers

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yunqing Zhao , Tianyu Pang , Chao Du , Xiao Yang , Chongxuan Li , Ngai-Man Cheung , Min Lin

Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Yi Ding , Lijun Li , Bing Cao , Jing Shao

Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend to visual modalities,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Shen Li , Liuyi Yao , Wujia Niu , Lan Zhang , Yaliang Li

The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of large language models (LLMs). Those MLLMs are typically…

Computation and Language · Computer Science 2024-10-10 Jiahui Gao , Renjie Pi , Tianyang Han , Han Wu , Lanqing Hong , Lingpeng Kong , Xin Jiang , Zhenguo Li

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…

Cryptography and Security · Computer Science 2026-05-15 Yi Wang , Hongye Qiu , Yue Xu , Sibei Yang , Zhan Qin , Minlie Huang , Wenjie Wang

Generative large vision-language models (LVLMs) have recently achieved impressive performance gains, and their user base is growing rapidly. However, the security of LVLMs, in particular in a long-context multi-turn setting, is largely…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Christian Schlarmann , Matthias Hein

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

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…

Cryptography and Security · Computer Science 2025-07-31 Chetan Pathade

Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…

Cryptography and Security · Computer Science 2024-11-11 Pete Janowczyk , Linda Laurier , Ave Giulietta , Arlo Octavia , Meade Cleti

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

Rapid deployment of vision-language models (VLMs) magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate…

Computation and Language · Computer Science 2025-09-24 DongGeon Lee , Joonwon Jang , Jihae Jeong , Hwanjo Yu

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Caiyong Piao , Zhiyuan Yan , Haoming Xu , Yunzhen Zhao , Kaiqing Lin , Feiyang Xu , Shuigeng Zhou

Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refine prompts using…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Jinwoo Jeon , JunHyeok Oh , Hayeong Lee , Byung-Jun Lee

Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Md Jueal Mia , M. Hadi Amini

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Xin Liu , Yichen Zhu , Jindong Gu , Yunshi Lan , Chao Yang , Yu Qiao

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.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Jiachen Sun , Changsheng Wang , Jiongxiao Wang , Yiwei Zhang , Chaowei Xiao

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Shuyang Hao , Bryan Hooi , Jun Liu , Kai-Wei Chang , Zi Huang , Yujun Cai

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

Large language models (LLMs) exhibit exceptional capabilities across various tasks but also pose risks by generating harmful content. Existing safety mechanisms, while improving model safety, often lead to overly cautious behavior and fail…

Machine Learning · Computer Science 2025-09-16 Peixuan Han , Cheng Qian , Xiusi Chen , Yuji Zhang , Heng Ji , Denghui Zhang