English
Related papers

Related papers: BlueSuffix: Reinforced Blue Teaming for Vision-Lan…

200 papers

The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content. Despite efforts to ethically align LLMs, these are often fragile and can be…

Computation and Language · Computer Science 2024-10-11 Zichuan Liu , Zefan Wang , Linjie Xu , Jinyu Wang , Lei Song , Tianchun Wang , Chunlin Chen , Wei Cheng , Jiang Bian

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These…

Cryptography and Security · Computer Science 2025-11-21 Wei Zhao , Zhe Li , Yige Li , Jun Sun

Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies that either fail to…

Computation and Language · Computer Science 2026-02-05 Francesco Giarrusso , Olga E. Sorokoletova , Vincenzo Suriani , Daniele Nardi

Large Vision-Language Models (VLMs) exhibit impressive multi-modal capabilities but suffer from prohibitive computational and memory demands, due to their long visual token sequences and massive parameter sizes. To address these issues,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Chengtao Lv , Bilang Zhang , Yang Yong , Ruihao Gong , Yushi Huang , Shiqiao Gu , Jiajun Wu , Yumeng Shi , Jinyang Guo , Wenya Wang

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

Cryptography and Security · Computer Science 2024-12-23 Hongyi Li , Jiawei Ye , Jie Wu , Tianjie Yan , Chu Wang , Zhixin Li

Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability. While many defense methods have been proposed, the trade-offs between safety and helpfulness, and their…

Cryptography and Security · Computer Science 2025-02-21 Zhuohang Long , Siyuan Wang , Shujun Liu , Yuhang Lai , Xuanjing Huang , Zhongyu Wei

As large Vision-Language Models (VLMs) gain prominence, ensuring their safe deployment has become critical. Recent studies have explored VLM robustness against jailbreak attacks-techniques that exploit model vulnerabilities to elicit…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Ruofan Wang , Juncheng Li , Yixu Wang , Bo Wang , Xiaosen Wang , Yan Teng , Yingchun Wang , Xingjun Ma , Yu-Gang Jiang

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Jiaming Zhang , Xingjun Ma , Xin Wang , Lingyu Qiu , Jiaqi Wang , Yu-Gang Jiang , Jitao Sang

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Computation and Language · Computer Science 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies,…

Computation and Language · Computer Science 2026-05-05 Mario Rodríguez Béjar , Francisco J. Cortés-Delgado , S. Braghin , Jose L. Hernández-Ramos

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Cryptography and Security · Computer Science 2025-09-29 Xiyu Zeng , Siyuan Liang , Liming Lu , Haotian Zhu , Enguang Liu , Jisheng Dang , Yongbin Zhou , Shuchao Pang

Large Language Models (LLMs) demonstrate impressive zero-shot performance across a wide range of natural language processing tasks. Integrating various modality encoders further expands their capabilities, giving rise to Multimodal Large…

Sound · Computer Science 2026-01-13 Hao Cheng , Erjia Xiao , Jing Shao , Yichi Wang , Le Yang , Chao Shen , Philip Torr , Jindong Gu , Renjing Xu

Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose significant security threats. Some defenses have been proposed…

Cryptography and Security · Computer Science 2025-02-12 Shenyi Zhang , Yuchen Zhai , Keyan Guo , Hongxin Hu , Shengnan Guo , Zheng Fang , Lingchen Zhao , Chao Shen , Cong Wang , Qian Wang

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, is it possible to use few-shot demonstrations to efficiently…

Computation and Language · Computer Science 2024-10-31 Xiaosen Zheng , Tianyu Pang , Chao Du , Qian Liu , Jing Jiang , Min Lin

Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Georgios Pantazopoulos , Amit Parekh , Malvina Nikandrou , Alessandro Suglia

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Juncheng Li , Yige Li , Hanxun Huang , Yunhao Chen , Xin Wang , Yixu Wang , Xingjun Ma , Yu-Gang Jiang

Though vertical federated learning (VFL) is generally considered to be privacy-preserving, recent studies have shown that VFL system is vulnerable to label inference attacks originating from various attack surfaces. Among these attacks, the…

Cryptography and Security · Computer Science 2026-01-23 Juntao Tan , Lan Zhang , Zhonghao Hu , Kai Yang , Peng Ran , Bo Li

The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards based on text embedding models serve as a fundamental…

Computation and Language · Computer Science 2025-05-20 Haoyu Liang , Youran Sun , Yunfeng Cai , Jun Zhu , Bo Zhang

System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…

Cryptography and Security · Computer Science 2026-02-03 Huseein Jawad , Nicolas Brunel

With LLM usage rapidly increasing, their vulnerability to jailbreaks that create harmful outputs are a major security risk. As new jailbreaking strategies emerge and models are changed by fine-tuning, continuous testing for security…