中文
相关论文

相关论文: CyberLLMInstruct: A Pseudo-malicious Dataset Revea…

200 篇论文

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

机器学习 · 统计学 2025-03-28 Pin-Yu Chen , Han Shen , Payel Das , Tianyi Chen

The rapid development of large language models (LLMs) has opened new avenues across various fields, including cybersecurity, which faces an evolving threat landscape and demand for innovative technologies. Despite initial explorations into…

密码学与安全 · 计算机科学 2024-12-05 Jie Zhang , Haoyu Bu , Hui Wen , Yongji Liu , Haiqiang Fei , Rongrong Xi , Lun Li , Yun Yang , Hongsong Zhu , Dan Meng

Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploited for malicious purposes. Although safety alignment datasets have been introduced to…

计算与语言 · 计算机科学 2026-04-20 Xiaorui Wu , Xiaofeng Mao , Fei Li , Xin Zhang , Xuanhong Li , Chong Teng , Donghong Ji , Zhuang Li

The rise of Large Language Models (LLMs) has revolutionized our comprehension of intelligence bringing us closer to Artificial Intelligence. Since their introduction, researchers have actively explored the applications of LLMs across…

Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…

软件工程 · 计算机科学 2026-01-14 Shaznin Sultana , Sadia Afreen , Nasir U. Eisty

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

机器学习 · 计算机科学 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

人工智能 · 计算机科学 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…

计算与语言 · 计算机科学 2024-08-06 Yuxia Wang , Zenan Zhai , Haonan Li , Xudong Han , Lizhi Lin , Zhenxuan Zhang , Jingru Zhao , Preslav Nakov , Timothy Baldwin

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

密码学与安全 · 计算机科学 2025-01-07 Shuai Zhao , Meihuizi Jia , Zhongliang Guo , Leilei Gan , Xiaoyu Xu , Xiaobao Wu , Jie Fu , Yichao Feng , Fengjun Pan , Luu Anh Tuan

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

密码学与安全 · 计算机科学 2025-07-30 Atil Samancioglu

Binary analysis remains pivotal in software security, offering insights into compiled programs without source code access. As large language models (LLMs) continue to excel in diverse language understanding and generation tasks, their…

软件工程 · 计算机科学 2025-05-13 Xiuwei Shang , Guoqiang Chen , Shaoyin Cheng , Benlong Wu , Li Hu , Gangyang Li , Weiming Zhang , Nenghai Yu

Instruction-tuned Large Language Models designed for coding tasks are increasingly employed as AI coding assistants. However, the cybersecurity vulnerabilities and implications arising from the widespread integration of these models are not…

密码学与安全 · 计算机科学 2025-03-10 Md Imran Hossen , Sai Venkatesh Chilukoti , Liqun Shan , Sheng Chen , Yinzhi Cao , Xiali Hei

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

密码学与安全 · 计算机科学 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Although Large Language Models (LLMs) show promising solutions to automated code generation, they often produce insecure code that threatens software security. Current approaches (e.g., SafeCoder) to improve secure code generation are…

软件工程 · 计算机科学 2025-11-25 Junjie Li , Fazle Rabbi , Bo Yang , Song Wang , Jinqiu Yang

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…

计算与语言 · 计算机科学 2024-10-29 Rongwu Xu , Yishuo Cai , Zhenhong Zhou , Renjie Gu , Haiqin Weng , Yan Liu , Tianwei Zhang , Wei Xu , Han Qiu

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

计算与语言 · 计算机科学 2024-10-01 Sachin Kumar

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

机器学习 · 计算机科学 2024-08-21 Luxi He , Mengzhou Xia , Peter Henderson

Large Language Models (LLMs) are transforming cybersecurity by enabling intelligent, adaptive, and automated approaches to threat detection, vulnerability assessment, and incident response. With their advanced language understanding and…

密码学与安全 · 计算机科学 2025-07-21 Niveen O. Jaffal , Mohammed Alkhanafseh , David Mohaisen

Large language models (LLMs) are demonstrating increasing prowess in cybersecurity applications, creating creating inherent risks alongside their potential for strengthening defenses. In this position paper, we argue that current efforts to…

密码学与安全 · 计算机科学 2025-02-04 Kamilė Lukošiūtė , Adam Swanda

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

机器学习 · 计算机科学 2026-04-24 Chengcan Wu , Zhixin Zhang , Zeming Wei , Yihao Zhang , Xiaokun Luan , Meng Sun