中文
相关论文

相关论文: On the Hardness of Junking LLMs

200 篇论文

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

计算与语言 · 计算机科学 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…

密码学与安全 · 计算机科学 2024-03-05 Daoyuan Wu , Shuai Wang , Yang Liu , Ning Liu

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

计算与语言 · 计算机科学 2025-03-26 Sravanti Addepalli , Yerram Varun , Arun Suggala , Karthikeyan Shanmugam , Prateek Jain

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

机器学习 · 计算机科学 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

计算与语言 · 计算机科学 2024-12-04 Yuping Lin , Pengfei He , Han Xu , Yue Xing , Makoto Yamada , Hui Liu , Jiliang Tang

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

密码学与安全 · 计算机科学 2024-12-03 Erick Galinkin , Martin Sablotny

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

密码学与安全 · 计算机科学 2025-11-04 Nathalie Kirch , Constantin Weisser , Severin Field , Helen Yannakoudakis , Stephen Casper

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…

计算与语言 · 计算机科学 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

计算与语言 · 计算机科学 2024-10-22 Yihua Zhou , Xiaochuan Shi

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

密码学与安全 · 计算机科学 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

计算与语言 · 计算机科学 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…

密码学与安全 · 计算机科学 2024-08-23 Jiawei Zhao , Kejiang Chen , Xiaojian Yuan , Weiming Zhang

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…

密码学与安全 · 计算机科学 2025-06-10 Yingchaojie Feng , Zhizhang Chen , Zhining Kang , Sijia Wang , Haoyu Tian , Wei Zhang , Minfeng Zhu , Wei Chen

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…

The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development efficiency and productivity. Notably, LLMs like GPT-4 have…

软件工程 · 计算机科学 2025-03-25 Sheng Ouyang , Yihao Qin , Bo Lin , Liqian Chen , Xiaoguang Mao , Shangwen Wang

Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's…

密码学与安全 · 计算机科学 2026-02-20 Yu Yin , Shuai Wang , Bevan Koopman , Guido Zuccon

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

密码学与安全 · 计算机科学 2026-02-27 Piyush Jaiswal , Aaditya Pratap , Shreyansh Saraswati , Harsh Kasyap , Somanath Tripathy

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…

密码学与安全 · 计算机科学 2025-12-30 Yangyang Guo , Yangyan Li , Mohan Kankanhalli

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security…

密码学与安全 · 计算机科学 2025-05-30 Bijoy Ahmed Saiem , MD Sadik Hossain Shanto , Rakib Ahsan , Md Rafi ur Rashid
‹ 上一页 1 2 3 10 下一页 ›