English
Related papers

Related papers: Safety Alignment for Vision Language Models

200 papers

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Artificial Intelligence · Computer Science 2025-02-18 Yingshui Tan , Yilei Jiang , Yanshi Li , Jiaheng Liu , Xingyuan Bu , Wenbo Su , Xiangyu Yue , Xiaoyong Zhu , Bo Zheng

Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing…

Computation and Language · Computer Science 2023-11-14 Rishabh Bhardwaj , Soujanya Poria

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

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

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…

Computer Vision and Pattern Recognition · Computer Science 2024-09-20 Hao Cheng , Erjia Xiao , Jindong Gu , Le Yang , Jinhao Duan , Jize Zhang , Jiahang Cao , Kaidi Xu , Renjing Xu

As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences…

Computation and Language · Computer Science 2024-07-11 Jiayang Song , Yuheng Huang , Zhehua Zhou , Lei Ma

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

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Artificial Intelligence · Computer Science 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities. Meanwhile, existing safety alignment methods…

Computers and Society · Computer Science 2026-02-03 Guanghao Zhou , Panjia Qiu , Cen Chen , Hongyu Li , Mingyuan Chu , Xin Zhang , Jun Zhou

Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Ailin Deng , Tri Cao , Zhirui Chen , Bryan Hooi

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown…

Software Engineering · Computer Science 2025-12-29 Jian Zhang , Chong Wang , Anran Li , Weisong Sun , Cen Zhang , Wei Ma , Yang Liu

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…

Computation and Language · Computer Science 2025-10-24 Jianhui Chen , Xiaozhi Wang , Zijun Yao , Yushi Bai , Lei Hou , Juanzi Li

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with…

Cryptography and Security · Computer Science 2025-03-07 Yangyang Guo , Fangkai Jiao , Liqiang Nie , Mohan Kankanhalli

3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Chao Liu , Ngai-Man Cheung

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Shashank Shriram , Srinivasa Perisetla , Aryan Keskar , Harsha Krishnaswamy , Tonko Emil Westerhof Bossen , Andreas Møgelmose , Ross Greer

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

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an open challenge. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xiangyu Yin , Jiaxu Liu , Zhen Chen , Jinwei Hu , Yi Dong , Xiaowei Huang , Wenjie Ruan

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

The safety alignment of current Large Language Models (LLMs) is vulnerable. Relatively simple attacks, or even benign fine-tuning, can jailbreak aligned models. We argue that many of these vulnerabilities are related to a shared underlying…

Cryptography and Security · Computer Science 2024-06-11 Xiangyu Qi , Ashwinee Panda , Kaifeng Lyu , Xiao Ma , Subhrajit Roy , Ahmad Beirami , Prateek Mittal , Peter Henderson

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Simone Caldarella , Massimiliano Mancini , Elisa Ricci , Rahaf Aljundi