English
Related papers

Related papers: Understanding and Rectifying Safety Perception Dis…

200 papers

Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Zihao Pan , Yu Tong , Weibin Wu , Jingyi Wang , Lifeng Chen , Zhe Zhao , Jiajia Wei , Yitong Qiao , Zibin Zheng

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries…

Artificial Intelligence · Computer Science 2026-02-24 Amirhossein Farzam , Majid Behabahani , Mani Malek , Yuriy Nevmyvaka , Guillermo Sapiro

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Computation and Language · Computer Science 2025-10-16 Juan Ren , Mark Dras , Usman Naseem

The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety…

Computation and Language · Computer Science 2025-06-10 Sooyung Choi , Jaehyeok Lee , Xiaoyuan Yi , Jing Yao , Xing Xie , JinYeong Bak

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…

Computation and Language · Computer Science 2025-05-09 Madhur Jindal , Saurabh Deshpande

Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Sihao Wu , Gaojie Jin , Wei Huang , Jianhong Wang , Xiaowei Huang

Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Wan-Cyuan Fan , Jiayun Luo , Declan Kutscher , Leonid Sigal , Ritwik Gupta

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Walter Gerych , Haoran Zhang , Kimia Hamidieh , Eileen Pan , Maanas Sharma , Thomas Hartvigsen , Marzyeh Ghassemi

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Trishna Chakraborty , Udita Ghosh , Aldair Ernesto Gongora , Ruben Glatt , Yue Dong , Jiachen Li , Amit K. Roy-Chowdhury , Chengyu Song

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

Cryptography and Security · Computer Science 2026-04-09 Quanchen Zou , Zonghao Ying , Moyang Chen , Wenzhuo Xu , Yisong Xiao , Yakai Li , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Large vision-language models (LVLMs) achieve strong multimodal performance, but still suffer from hallucinations caused by unstable visual grounding and over-reliance on language priors. Existing training-free decoding methods typically…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Xinyun Liu

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Cryptography and Security · Computer Science 2025-06-10 Yukai Zhou , Sibei Yang , Wenjie Wang

Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare. However, their ability to produce deceptive outputs, whether intentionally or inadvertently, poses…

Computation and Language · Computer Science 2025-10-17 Marwa Abdulhai , Ryan Cheng , Aryansh Shrivastava , Natasha Jaques , Yarin Gal , Sergey Levine

Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM safety.…

Machine Learning · Computer Science 2026-04-13 Jinqi Luo , Jinyu Yang , Tal Neiman , Lei Fan , Bing Yin , Son Tran , Mubarak Shah , René Vidal

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Computation and Language · Computer Science 2026-02-03 Yuxuan Lu , Yongkang Guo , Yuqing Kong

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal perception and generation, yet their safety alignment remains a critical challenge.Existing defenses and vulnerable to multimodal jailbreaks, as visual…

Artificial Intelligence · Computer Science 2025-10-21 MingSheng Li , Guangze Zhao , Sichen Liu

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks,…

Machine Learning · Computer Science 2026-02-18 Nicolas Buzeta , Felipe del Rio , Cristian Hinostroza , Denis Parra , Hans Lobel , Rodrigo Toro Icarte

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Xiang Fang , Wanlong Fang , Changshuo Wang

There has been an increasing interest in the alignment of large language models (LLMs) with human values. However, the safety issues of their integration with a vision module, or vision language models (VLMs), remain relatively…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Xijia Tao , Shuai Zhong , Lei Li , Qi Liu , Lingpeng Kong

Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias-the…

Computation and Language · Computer Science 2026-05-26 Yangneng Chen , Jing Li