English
Related papers

Related papers: Directional Embedding Smoothing for Robust Vision …

200 papers

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel…

Cryptography and Security · Computer Science 2026-05-12 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Haichang Gao

Multimodal large language models (MLLMs) have achieved impressive performance across diverse tasks by jointly reasoning over textual and visual inputs. Despite their success, these models remain highly vulnerable to adversarial…

Machine Learning · Computer Science 2025-11-03 Guangzhi Su , Shuchang Huang , Yutong Ke , Zhuohang Liu , Long Qian , Kaizhu Huang

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

Machine Learning · Computer Science 2025-07-09 Wenyi Wu , Zixuan Song , Kun Zhou , Yifei Shao , Zhiting Hu , Biwei Huang

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

Stable pre-training is essential for achieving better-performing language models. However, tracking pre-training stability by calculating gradient variance at every step is impractical due to the significant computational costs. We explore…

Computation and Language · Computer Science 2024-09-13 Woojin Chung , Jiwoo Hong , Na Min An , James Thorne , Se-Young Yun

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms to elicit restricted content generation. Existing black-box…

Computation and Language · Computer Science 2025-06-23 Lei Jiang , Zixun Zhang , Zizhou Wang , Xiaobing Sun , Zhen Li , Liangli Zhen , Xiaohua Xu

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Cryptography and Security · Computer Science 2026-05-05 Lingxi Zhang , Guangtao Zheng , Hanjie Chen

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Hashmat Shadab Malik , Fahad Shamshad , Muzammal Naseer , Karthik Nandakumar , Fahad Khan , Salman Khan

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,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Ravikumar Balakrishnan , Sanket Mendapara , Ankit Garg

Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to jailbreaking attacks that bypass safety mechanisms and drive unsafe or physically harmful behaviors in…

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defense using tensor…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Het Patel , Muzammil Allie , Qian Zhang , Jia Chen , Evangelos E. Papalexakis

The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable attacks across…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Ruofan Wang , Xin Wang , Yang Yao , Juncheng Li , Xuan Tong , Xingjun Ma

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…

Artificial Intelligence · Computer Science 2025-05-27 Pooneh Mousavi , Shubham Gupta , Cem Subakan , Mirco Ravanelli

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Ruofan Wang , Xingjun Ma , Hanxu Zhou , Chuanjun Ji , Guangnan Ye , Yu-Gang Jiang

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow…

Artificial Intelligence · Computer Science 2025-10-06 Zhaorun Chen , Xun Liu , Mintong Kang , Jiawei Zhang , Minzhou Pan , Shuang Yang , Bo Li

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Jingru Li , Wei Ren , Tianqing Zhu

This study evaluates the effectiveness of Vision Language Models (VLMs) in representing and utilizing multimodal content for fact-checking. To be more specific, we investigate whether incorporating multimodal content improves performance…

Computation and Language · Computer Science 2024-12-09 Recep Firat Cekinel , Pinar Karagoz , Cagri Coltekin