计算机应用研究2024，Vol.41Issue(11)：3447-3454,8.DOI:10.19734/j.issn.1001-3695.2024.01.0061
基于双注意力机制和改进对抗训练的漏洞分类方法
Vulnerability classification method based on double-attention mechanism and adversarial training
摘要
Abstract
Vulnerability reports play a pivotal role in cybersecurity,and the ever-growing number of vulnerabilities challenges the efficiency and accuracy of vulnerability classification.To alleviate issues with deep learning models in vulnerability classifi-cation,which often fail to focus on significant features and are prone to overfitting,this paper introduced a novel vulnerability classification approach based on a double attention mechanism and improved adversarial training.Firstly,this paper proposed the TextCNN-DA model,which augmented the conventional TextCNN with spatial and channel attention mechanisms to en-hance focus on pertinent features.Furthermore,this paper introduced the SWV-FGM algorithm for adversarial training to in-crease the robustness and generalization of the model.Comparative analysis with other baseline algorithms on a vulnerability dataset,and specific performance evaluation across different vulnerability types,show that the proposed method outperforms in several key metrics such as accuracy and macro-F1,effectively advancing vulnerability classification tasks.关键词
网络安全/漏洞分类/注意力机制/对抗训练Key words
cyber security/vulnerability classification/attention mechanism/adversarial training分类
信息技术与安全科学引用本文复制引用
杨尽能,李汶珊,何俊江,周绍鸿,李涛,王运鹏..基于双注意力机制和改进对抗训练的漏洞分类方法[J].计算机应用研究,2024,41(11):3447-3454,8.基金项目
国家重点研发计划资助项目(2020YFB1805400) （2020YFB1805400）
国家自然科学基金资助项目(62032002,62101358) （62032002,62101358）
四川省科技计划重点研发项目(2023YFG0294) （2023YFG0294）
四川省自然科学青年基金资助项目(2023NSFSC1395) （2023NSFSC1395）
