| 引用本文: | 唐家昕,王璇,赖伟,路则雨,郭肇强,杨已彪,周毓明.深度学习驱动的软件漏洞预测: 问题、进展与挑战.软件学报,2025,36(11):4906-4952 |
| |
|
| 摘要: |
| 软件漏洞是软件中易于被攻击利用的代码片段, 确保软件不易受到攻击是软件开发中必须重视的安全性需求. 软件漏洞预测是指对软件代码进行分析预测, 从而及时找出潜在的漏洞. 深度学习驱动的软件漏洞预测是近年来一个热门的研究领域, 时间跨度大、研究数目众多、研究成果丰厚. 为梳理相关研究成果、总结研究热点, 对2017–2024年间发表的151篇深度学习驱动的软件漏洞预测相关的文献进行综述, 总结相关文献的研究问题、进展以及遇到的问题与挑战等内容, 为后续研究提供参考. |
| 关键词: 软件漏洞 深度学习 预测 软件质量 特征表示 |
| DOI：10.13328/j.cnki.jos.007376 |
| 分类号: |
| 基金项目:国家自然科学基金(62172205) |
|
| Deep-learning-driven Software Vulnerability Prediction: Problems, Progress, and Challenges |
|
TANG Jia-Xin, WANG Xuan, LAI Wei, LU Ze-Yu, GUO Zhao-Qiang, YANG Yi-Biao, ZHOU Yu-Ming
|
|
Department of Computer Science and Technology, Nanjing University, Nanjing 210094, China
|
| Abstract: |
| Software vulnerabilities are code segments in software that are prone to exploitation. Ensuring that software is not easily attacked is a crucial security requirement in software development. Software vulnerability prediction involves analyzing and predicting potential vulnerabilities in software code. Deep learning-driven software vulnerability prediction has become a popular research field in recent years, with a long time span, numerous studies, and substantial research achievements. To review relevant research findings and summarize the research hotspots, a survey of 151 studies related to deep learning-driven software vulnerability prediction published between 2017 and 2024 is conducted. It summarizes the research problems, progress, and challenges discussed in the literature, providing a reference for future research. |
| Key words: software vulnerability deep learning prediction software quality feature representation |
