中文
相关论文

相关论文: Geneshift: Impact of different scenario shift on J…

200 篇论文

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

密码学与安全 · 计算机科学 2025-11-21 Zhen Sun , Zongmin Zhang , Deqi Liang , Han Sun , Yule Liu , Yun Shen , Xiangshan Gao , Yilong Yang , Shuai Liu , Yutao Yue , Xinlei He

Recent studies developed jailbreaking attacks, which construct jailbreaking prompts to fool LLMs into responding to harmful questions. Early-stage jailbreaking attacks require access to model internals or significant human efforts. More…

密码学与安全 · 计算机科学 2025-01-28 Xuan Chen , Yuzhou Nie , Wenbo Guo , Xiangyu Zhang

Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM…

密码学与安全 · 计算机科学 2026-03-26 Zheng Zhang , Peilin Zhao , Deheng Ye , Hao Wang

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Large language models (LLMs), designed to provide helpful and safe responses, often rely on alignment techniques to align with user intent and social guidelines. Unfortunately, this alignment can be exploited by malicious actors seeking to…

计算与语言 · 计算机科学 2024-08-06 Raz Lapid , Ron Langberg , Moshe Sipper

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

密码学与安全 · 计算机科学 2025-05-29 Yao Huang , Yitong Sun , Shouwei Ruan , Yichi Zhang , Yinpeng Dong , Xingxing Wei

This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to…

密码学与安全 · 计算机科学 2026-05-18 Yue Liu , Xiaoxin He , Miao Xiong , Jinlan Fu , Shumin Deng , Yingwei Ma , Jiaheng Zhang , Bryan Hooi

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

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

Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker observes…

密码学与安全 · 计算机科学 2026-05-29 Junke Zhang , Jianwei Wang , Sishuo Chen , Yizhang He , Qingshuai Feng , Zhengyi Yang

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

Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique ``jailbreak prompt'' can circumvent safety-aligned measures and induce LLMs to output malicious content.…

密码学与安全 · 计算机科学 2025-08-28 Xi Wang , Songlei Jian , Shasha Li , Xiaopeng Li , Bin Ji , Jun Ma , Xiaodong Liu , Jing Wang , Feilong Bao , Jianfeng Zhang , Baosheng Wang , Jie Yu

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

密码学与安全 · 计算机科学 2024-01-31 Jie Li , Yi Liu , Chongyang Liu , Ling Shi , Xiaoning Ren , Yaowen Zheng , Yang Liu , Yinxing Xue

While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such…

密码学与安全 · 计算机科学 2025-01-03 Miao Yu , Junfeng Fang , Yingjie Zhou , Xing Fan , Kun Wang , Shirui Pan , Qingsong Wen

Defense in large language models (LLMs) is crucial to counter the numerous attackers exploiting these systems to generate harmful content through manipulated prompts, known as jailbreak attacks. Although many defense strategies have been…

密码学与安全 · 计算机科学 2024-12-11 Bocheng Chen , Hanqing Guo , Qiben Yan

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

密码学与安全 · 计算机科学 2025-10-10 Xiangfang Li , Yu Wang , Bo Li

Large language models (LLMs) have demonstrated significant utility in a wide range of applications; however, their deployment is plagued by security vulnerabilities, notably jailbreak attacks. These attacks manipulate LLMs to generate…

计算与语言 · 计算机科学 2025-03-12 Wenlong Meng , Fan Zhang , Wendao Yao , Zhenyuan Guo , Yuwei Li , Chengkun Wei , Wenzhi Chen

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

密码学与安全 · 计算机科学 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting…

计算与语言 · 计算机科学 2024-04-25 Kazuhiro Takemoto

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…

密码学与安全 · 计算机科学 2024-12-23 Hongyi Li , Jiawei Ye , Jie Wu , Tianjie Yan , Chu Wang , Zhixin Li
‹ 上一页 1 2 3 10 下一页 ›