中文
相关论文

相关论文: Safeguarding Large Language Models in Real-time wi…

200 篇论文

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

密码学与安全 · 计算机科学 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

计算与语言 · 计算机科学 2025-03-07 Honglin Mu , Han He , Yuxin Zhou , Yunlong Feng , Yang Xu , Libo Qin , Xiaoming Shi , Zeming Liu , Xudong Han , Qi Shi , Qingfu Zhu , Wanxiang Che

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

密码学与安全 · 计算机科学 2025-09-05 Chuhan Zhang , Ye Zhang , Bowen Shi , Yuyou Gan , Tianyu Du , Shouling Ji , Dazhan Deng , Yingcai Wu

Jailbreaking large language models (LLMs) has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit…

密码学与安全 · 计算机科学 2026-02-23 Sri Durga Sai Sowmya Kadali , Evangelos E. Papalexakis

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

机器学习 · 计算机科学 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into…

密码学与安全 · 计算机科学 2024-10-02 Zhiyuan Yu , Xiaogeng Liu , Shunning Liang , Zach Cameron , Chaowei Xiao , Ning Zhang

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves…

密码学与安全 · 计算机科学 2026-01-09 Zhengyuan Jiang , Yuepeng Hu , Yuchen Yang , Yinzhi Cao , Neil Zhenqiang Gong

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…

密码学与安全 · 计算机科学 2025-06-10 Yifan Jiang , Kriti Aggarwal , Tanmay Laud , Kashif Munir , Jay Pujara , Subhabrata Mukherjee

Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the…

人机交互 · 计算机科学 2024-07-04 Zhihua Jin , Shiyi Liu , Haotian Li , Xun Zhao , Huamin Qu

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

机器学习 · 计算机科学 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

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,…

计算与语言 · 计算机科学 2025-05-27 Binhao Ma , Hanqing Guo , Zhengping Jay Luo , Rui Duan

Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with diverse attributes, such as contextual coherence and…

机器学习 · 计算机科学 2024-06-10 Xingang Guo , Fangxu Yu , Huan Zhang , Lianhui Qin , Bin Hu

We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…

计算与语言 · 计算机科学 2025-05-13 Weiliang Zhao , Daniel Ben-Levi , Wei Hao , Junfeng Yang , Chengzhi Mao

Large language models have drawn significant attention to the challenge of safe alignment, especially regarding jailbreak attacks that circumvent security measures to produce harmful content. To address the limitations of existing methods…

人工智能 · 计算机科学 2024-11-05 Hanqing Liu , Lifeng Zhou , Huanqian Yan

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

密码学与安全 · 计算机科学 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…

密码学与安全 · 计算机科学 2024-06-21 Jiongxiao Wang , Jiazhao Li , Yiquan Li , Xiangyu Qi , Junjie Hu , Yixuan Li , Patrick McDaniel , Muhao Chen , Bo Li , Chaowei Xiao

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, making MLLMs susceptible to multimodal jailbreak attacks and…

密码学与安全 · 计算机科学 2025-12-04 Beitao Chen , Xinyu Lyu , Lianli Gao , Jingkuan Song , Heng Tao Shen

Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…

计算与语言 · 计算机科学 2025-10-28 Havva Alizadeh Noughabi , Julien Serbanescu , Fattane Zarrinkalam , Ali Dehghantanha

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

密码学与安全 · 计算机科学 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria