RAGN: Detecting unknown malicious network traffic using a robust adaptive graph neural network

IF 4.4 2区 计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE Computer Networks Pub Date : 2025-03-10 DOI:10.1016/j.comnet.2025.111184
Ernest Akpaku , Jinfu Chen , Mukhtar Ahmed , Francis Kwadzo Agbenyegah , William Leslie Brown-Acquaye
{"title":"RAGN: Detecting unknown malicious network traffic using a robust adaptive graph neural network","authors":"Ernest Akpaku ,&nbsp;Jinfu Chen ,&nbsp;Mukhtar Ahmed ,&nbsp;Francis Kwadzo Agbenyegah ,&nbsp;William Leslie Brown-Acquaye","doi":"10.1016/j.comnet.2025.111184","DOIUrl":null,"url":null,"abstract":"<div><div>As network environments evolve, detecting unknown malicious network traffic becomes increasingly challenging due to the dynamic and sophisticated nature of modern cyberattacks. Graph Attention Networks (GATs) have shown promise in modeling complex network interactions but remain vulnerable to adversarial attacks that exploit weaknesses in the graph structure. In this work, we propose the Robust Adaptive Graph Neural Network (RAGN), an enhanced GAT-based framework that introduces adaptive attention mechanisms to improve detection accuracy and robustness against adversarial manipulations in network traffic graphs. RAGN iteratively adjusts the graph structure and feature space to suppress adversarial perturbations by assigning lower attention scores to unreliable edges and refining feature representations based on the feature smoothness regularization principle. To assess the robustness of the proposed RAGN model and compare it with baseline models, we introduced an effective dynamic graph attack method known as Semantic-Preserving Adversarial Node Injection (SPAN). We benchmarked its performance against state-of-the-art graph attack methods, including DICE, DGA, and RWCS. SPAN incrementally injects small batches of malicious nodes, refining their edges and features to target both the structural and temporal aspects of dynamic graphs. It preserves semantic integrity, and generates effective yet imperceptible perturbations, providing a rigorous test of the resilience of graph neural networks. Experiments conducted on four datasets, demonstrate that RAGN demonstrates robustness against adversarial, and zero-day attacks. It also demonstrates resilience against targeted, malicious node injection attacks in dynamic network environments. RAGN demonstrated consistent robustness, with misclassification rates increasing only marginally (by less than 1.2%) even under significant dynamic changes.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111184"},"PeriodicalIF":4.4000,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1389128625001525","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0

Abstract

As network environments evolve, detecting unknown malicious network traffic becomes increasingly challenging due to the dynamic and sophisticated nature of modern cyberattacks. Graph Attention Networks (GATs) have shown promise in modeling complex network interactions but remain vulnerable to adversarial attacks that exploit weaknesses in the graph structure. In this work, we propose the Robust Adaptive Graph Neural Network (RAGN), an enhanced GAT-based framework that introduces adaptive attention mechanisms to improve detection accuracy and robustness against adversarial manipulations in network traffic graphs. RAGN iteratively adjusts the graph structure and feature space to suppress adversarial perturbations by assigning lower attention scores to unreliable edges and refining feature representations based on the feature smoothness regularization principle. To assess the robustness of the proposed RAGN model and compare it with baseline models, we introduced an effective dynamic graph attack method known as Semantic-Preserving Adversarial Node Injection (SPAN). We benchmarked its performance against state-of-the-art graph attack methods, including DICE, DGA, and RWCS. SPAN incrementally injects small batches of malicious nodes, refining their edges and features to target both the structural and temporal aspects of dynamic graphs. It preserves semantic integrity, and generates effective yet imperceptible perturbations, providing a rigorous test of the resilience of graph neural networks. Experiments conducted on four datasets, demonstrate that RAGN demonstrates robustness against adversarial, and zero-day attacks. It also demonstrates resilience against targeted, malicious node injection attacks in dynamic network environments. RAGN demonstrated consistent robustness, with misclassification rates increasing only marginally (by less than 1.2%) even under significant dynamic changes.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
随着网络环境的发展,由于现代网络攻击的动态性和复杂性,检测未知恶意网络流量变得越来越具有挑战性。图注意网络(GAT)在模拟复杂的网络交互方面已显示出良好的前景,但仍然容易受到利用图结构弱点的恶意攻击。在这项工作中,我们提出了鲁棒性自适应图神经网络(RAGN),这是一种基于 GAT 的增强型框架,它引入了自适应关注机制,以提高检测精度和鲁棒性,抵御网络流量图中的恶意操作。RAGN 会迭代调整图结构和特征空间,通过为不可靠的边分配较低的注意力分数,并根据特征平滑正则化原则完善特征表示,从而抑制对抗性扰动。为了评估所提出的 RAGN 模型的鲁棒性并将其与基线模型进行比较,我们引入了一种有效的动态图攻击方法,即语义保留对抗性节点注入(SPAN)。我们将其性能与最先进的图攻击方法(包括 DICE、DGA 和 RWCS)进行了比较。SPAN 以增量方式注入小批恶意节点,完善其边缘和特征,以针对动态图的结构和时间方面。它能保持语义的完整性,并产生有效但不易察觉的扰动,为图神经网络的恢复能力提供了严格的测试。在四个数据集上进行的实验表明,RAGN 对对抗性攻击和零日攻击具有很强的抵御能力。它还能在动态网络环境中抵御有针对性的恶意节点注入攻击。RAGN 表现出了一贯的鲁棒性,即使在显著的动态变化下,误分类率也仅略有增加(增幅小于 1.2%)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Computer Networks
Computer Networks 工程技术-电信学
CiteScore
10.80
自引率
3.60%
发文量
434
审稿时长
8.6 months
期刊介绍: Computer Networks is an international, archival journal providing a publication vehicle for complete coverage of all topics of interest to those involved in the computer communications networking area. The audience includes researchers, managers and operators of networks as well as designers and implementors. The Editorial Board will consider any material for publication that is of interest to those groups.
期刊最新文献
Deep Reinforcement Learning and SQP-driven task offloading decisions in vehicular edge computing networks Decentralized traffic detection utilizing blockchain-federated learning with quality-driven aggregation RAGN: Detecting unknown malicious network traffic using a robust adaptive graph neural network Editorial Board Social network botnet attack mitigation model for cloud
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1