首页|新增未知攻击场景下的工业互联网恶意流量识别方法

新增未知攻击场景下的工业互联网恶意流量识别方法

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
针对工业互联网中新增未知攻击所引发的流量数据分布偏移问题,提出了一种基于邻域过滤和稳定学习的恶意流量识别方法,旨在增强现有图神经网络模型在识别已知类恶意流量时的有效性和鲁棒性.该方法首先对流量数据进行图结构建模,捕获通信行为中的拓扑关系与交互模式;然后,基于有偏采样的邻域过滤机制划分流量子图,消除通信行为间的伪同质性;最后,应用图表示学习和稳定学习策略,结合自适应样本加权与协同损失优化方法,实现高维流量特征的统计独立性.2个基准数据集上的实验结果表明,相较对比方法,所提方法在新增未知攻击场景下的识别性能提升超过2.7%,展示了其在工业互联网环境下的高效性和实用性.
Identification method for malicious traffic in industrial Internet under new unknown attack scenarios
Aiming at the problem of traffic data distribution shift caused by new unknown attacks in the industrial Inter-net,a malicious traffic identification method based on neighborhood filtering and stable learning was proposed to en-hance the effectiveness and robustness of the existing graph neural network model in identifying known malicious traffic.Firstly,the graph structure of the traffic data was modeled to capture the topological relationship and interaction mode in communication behavior.Secondly,the traffic subgraph was divided based on the neighborhood filtering mechanism of biased sampling to eliminate the pseudo-homogeneity between communication behaviors.Finally,the statistical indepen-dence of high-dimensional traffic features was realized by applying graph representation learning and stable learning strategies,combined with adaptive sample weighting and collaborative loss optimization methods.The experimental re-sults on two benchmark datasets show that compared with the baseline method,the recognition performance of the pro-posed method is increased by more than 2.7%in the new unknown attack scenario,which shows its high efficiency and practicability in the industrial Internet environment.

industrial Internetmalicious traffic identificationgraph neural networkneighborhood filteringstable learning

曾凡一、苘大鹏、许晨、韩帅、王焕然、周雪、李欣纯、杨武

展开 >

哈尔滨工程大学计算机科学与技术学院,黑龙江 哈尔滨 150009

工业互联网 恶意流量识别 图神经网络 邻域过滤 稳定学习

国家重点研发计划基金资助项目国家自然科学基金资助项目国家自然科学基金资助项目国家自然科学基金资助项目国家自然科学基金资助项目国家自然科学基金资助项目黑龙江省自然科学基金资助项目

2021YFB3101403U2003206U20B2048U21B2019U22A203662272127TD2022F001

2024

10.11959/j.issn.1000-436x.2024093

通信学报
中国通信学会

通信学报

CSTPCD北大核心
影响因子：1.265
ISSN：1000-436X
年,卷(期)：2024.45(6)