中文
相关论文

相关论文: Behind the Mask: Benchmarking Camouflaged Jailbrea…

200 篇论文

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

密码学与安全 · 计算机科学 2025-07-18 Yi Nian , Shenzhe Zhu , Yuehan Qin , Li Li , Ziyi Wang , Chaowei Xiao , Yue Zhao

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

计算与语言 · 计算机科学 2024-10-08 Sarah Ball , Frauke Kreuter , Nina Panickssery

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…

计算与语言 · 计算机科学 2025-08-15 Ayana Hussain , Patrick Zhao , Nicholas Vincent

Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment. Existing defense strategies typically rely on predefined static criteria to differentiate between harmful and benign prompts.…

密码学与安全 · 计算机科学 2025-05-21 Rui Pu , Chaozhuo Li , Rui Ha , Litian Zhang , Lirong Qiu , Xi Zhang

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

Large Audio Language Models (LALMs) have made significant progress. While increasingly deployed in real-world applications, LALMs face growing safety risks from jailbreak attacks that bypass safety alignment. However, there remains a lack…

密码学与安全 · 计算机科学 2026-03-03 Zifan Peng , Yule Liu , Zhen Sun , Mingchen Li , Zeren Luo , Jingyi Zheng , Wenhan Dong , Xinlei He , Xuechao Wang , Yingjie Xue , Shengmin Xu , Xinyi Huang

The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine…

密码学与安全 · 计算机科学 2024-10-21 Baha Rababah , Shang , Wu , Matthew Kwiatkowski , Carson Leung , Cuneyt Gurcan Akcora

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies…

密码学与安全 · 计算机科学 2025-01-03 Johan Wahréus , Ahmed Mohamed Hussain , Panos Papadimitratos

Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety…

密码学与安全 · 计算机科学 2025-05-27 Guobin Shen , Dongcheng Zhao , Linghao Feng , Xiang He , Jihang Wang , Sicheng Shen , Haibo Tong , Yiting Dong , Jindong Li , Xiang Zheng , Yi Zeng

Detecting jailbreak attempts in clinical training large language models (LLMs) requires accurate modeling of linguistic deviations that signal unsafe or off-task user behavior. Prior work on the 2-Sigma clinical simulation platform showed…

人工智能 · 计算机科学 2026-02-17 Tri Nguyen , Huy Hoang Bao Le , Lohith Srikanth Pentapalli , Laurah Turner , Kelly Cohen

Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…

计算与语言 · 计算机科学 2025-05-20 Linghan Huang , Haolin Jin , Zhaoge Bi , Pengyue Yang , Peizhou Zhao , Taozhao Chen , Xiongfei Wu , Lei Ma , Huaming Chen

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 rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts…

密码学与安全 · 计算机科学 2025-10-22 Hanbin Hong , Shuya Feng , Nima Naderloui , Shenao Yan , Jingyu Zhang , Biying Liu , Ali Arastehfard , Heqing Huang , Yuan Hong

Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful…

计算与语言 · 计算机科学 2024-02-27 Huijie Lv , Xiao Wang , Yuansen Zhang , Caishuang Huang , Shihan Dou , Junjie Ye , Tao Gui , Qi Zhang , Xuanjing Huang

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety.…

密码学与安全 · 计算机科学 2024-07-29 Zhangchen Xu , Fengqing Jiang , Luyao Niu , Jinyuan Jia , Bill Yuchen Lin , Radha Poovendran

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…

人工智能 · 计算机科学 2025-09-30 Zhaoqi Wang , Daqing He , Zijian Zhang , Xin Li , Liehuang Zhu , Meng Li , Jiamou Liu

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

密码学与安全 · 计算机科学 2025-12-17 Fan Yang

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

密码学与安全 · 计算机科学 2024-09-10 Divyanshu Kumar , Anurakt Kumar , Sahil Agarwal , Prashanth Harshangi

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

密码学与安全 · 计算机科学 2025-08-14 Boyuan Chen , Minghao Shao , Abdul Basit , Siddharth Garg , Muhammad Shafique

Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that this vulnerability stems from distributional discrepancies…

计算与语言 · 计算机科学 2026-04-27 Jingyu Peng , Maolin Wang , Nan Wang , Jiatong Li , Yuchen Li , Yuyang Ye , Wanyu Wang , Pengyue Jia , Kai Zhang , Xiangyu Zhao