English
Related papers

Related papers: Mitigating Many-Shot Jailbreaking

200 papers

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…

Computation and Language · Computer Science 2025-05-27 Binhao Ma , Hanqing Guo , Zhengping Jay Luo , Rui Duan

Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs. Most jailbreak prompt…

Computation and Language · Computer Science 2024-02-28 Xiaoxia Li , Siyuan Liang , Jiyi Zhang , Han Fang , Aishan Liu , Ee-Chien Chang

With the enhanced performance of large models on natural language processing tasks, potential moral and ethical issues of large models arise. There exist malicious attackers who induce large models to jailbreak and generate information…

Artificial Intelligence · Computer Science 2024-04-04 Qianqiao Xu , Zhiliang Tian , Hongyan Wu , Zhen Huang , Yiping Song , Feng Liu , Dongsheng Li

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Large Language Models (LLMs) are a double-edged sword capable of generating harmful misinformation -- inadvertently, or when prompted by "jailbreak" attacks that attempt to produce malicious outputs. LLMs could, with additional research, be…

Computation and Language · Computer Science 2025-08-15 Ayana Hussain , Patrick Zhao , Nicholas Vincent

The widespread adoption of thinking mode in large language models (LLMs) has significantly enhanced complex task processing capabilities while introducing new security risks. When subjected to jailbreak attacks, the step-by-step reasoning…

Cryptography and Security · Computer Science 2026-03-12 Fan Yang

Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to perform adversarial training (AT)-based alignment, i.e.,…

Machine Learning · Computer Science 2026-02-03 Shaopeng Fu , Liang Ding , Jingfeng Zhang , Di Wang

As large language models (LLMs) become more integral to society and technology, ensuring their safety becomes essential. Jailbreak attacks exploit vulnerabilities to bypass safety guardrails, posing a significant threat. However, the…

Cryptography and Security · Computer Science 2025-07-08 Xiaomeng Hu , Pin-Yu Chen , Tsung-Yi Ho

Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, they remain vulnerable to jailbreak attacks, which exploit weaknesses in their safety alignment to…

Cryptography and Security · Computer Science 2025-08-29 Wenzhuo Xu , Zhipeng Wei , Xiongtao Sun , Zonghao Ying , Deyue Zhang , Dongdong Yang , Xiangzheng Zhang , Quanchen Zou

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed…

Cryptography and Security · Computer Science 2025-06-10 Yifan Jiang , Kriti Aggarwal , Tanmay Laud , Kashif Munir , Jay Pujara , Subhabrata Mukherjee

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

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jailbreaking works, which makes it hard to develop effective…

Computation and Language · Computer Science 2025-05-22 Lang Gao , Jiahui Geng , Xiangliang Zhang , Preslav Nakov , Xiuying Chen

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

Computation and Language · Computer Science 2025-11-05 Berk Atil , Rebecca J. Passonneau , Fred Morstatter

While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities. We present MIRAGE, a novel multimodal jailbreak…

Computation and Language · Computer Science 2025-03-26 Wenhao You , Bryan Hooi , Yiwei Wang , Youke Wang , Zong Ke , Ming-Hsuan Yang , Zi Huang , Yujun Cai

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

LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks that elicit harmful behaviors without explicit policy violations. While a growing body of…

Cryptography and Security · Computer Science 2026-05-05 Jindong Li , Ying Liu , Yali Fu , Jinjing Zhu , Leyao Wang , Menglin Yang , Rex Ying

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Computation and Language · Computer Science 2024-02-26 Yanrui Du , Sendong Zhao , Ming Ma , Yuhan Chen , Bing Qin

Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or trained adversarial generators, but are slow,…

Computation and Language · Computer Science 2025-07-08 James Beetham , Souradip Chakraborty , Mengdi Wang , Furong Huang , Amrit Singh Bedi , Mubarak Shah

Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking…

Cryptography and Security · Computer Science 2025-08-19 Weiwei Qi , Shuo Shao , Wei Gu , Tianhang Zheng , Puning Zhao , Zhan Qin , Kui Ren