Jin Zhiping, Duan Ke, Chen Changhui, He Meirong, Jiang Shan, Xue Hanxiao
School of Information Engineering, Zhongshan Polytechnic, Zhongshan, China.
Guangzhou Panyu Polytechnic, Guangzhou, China.
Heliyon. 2024 Aug 11;10(16):e35962. doi: 10.1016/j.heliyon.2024.e35962. eCollection 2024 Aug 30.
The current popular traffic classification methods based on feature engineering and machine learning are difficult to obtain suitable traffic feature sets for multiple traffic classification tasks. Besides, data privacy policies prohibit network operators from collecting and sharing traffic data that might compromise user privacy. To address these challenges, we propose FedETC, a federated learning framework that allows multiple participants to learn global traffic classifiers, while keeping locally encrypted traffic invisible to other participants. In addition, FedETC adopts one-dimensional convolutional neural network as the base model, which avoids manual traffic feature design. In the experiments, we evaluate the FedETC framework for the tasks of both application identification and traffic characterization in a publicly available real-world dataset. The results show that FedETC can achieve promising accuracy rates that are close to centralized learning schemes.
当前基于特征工程和机器学习的流行流量分类方法难以获得适用于多个流量分类任务的流量特征集。此外，数据隐私政策禁止网络运营商收集和共享可能危及用户隐私的流量数据。为应对这些挑战，我们提出了FedETC，这是一个联邦学习框架，它允许多个参与者学习全局流量分类器，同时对其他参与者隐藏本地加密的流量。此外，FedETC采用一维卷积神经网络作为基础模型，避免了人工流量特征设计。在实验中，我们在一个公开可用的真实世界数据集中评估了FedETC框架在应用识别和流量特征描述任务方面的性能。结果表明，FedETC可以实现接近集中式学习方案的可观准确率。
