【摘要】 大数据时代的到来使得数据成为社会发展的重要战略资源。然而随着网络环境日趋复杂化,隐私泄露和恶意攻击事件层出不穷。联邦学习作为一种新型数据共享模型,能够在保护数据隐私的前提下进行数据共享,有效解决了传统入侵检测模型的弊端。文章首先介绍了联邦学习及入侵检测模型的构成及特点,提出了基于联邦学习的入侵检测机制,并深入分析了该检测机制在检测准确率及效率上有效提升的可行性。通过对模型进行需求分析和设计,并以函数编程进行模拟仿真实验,实现原型系统开发。实验表明联邦学习机制能够在保证参与客户端数据隐私安全的前提下实现多方攻击行为日志的共享。多组控制变量的对照实验表明,基于联邦学习的入侵检测机制在检测准确率及效率上得到明显改善。更多还原

【Abstract】 With the advent of the era of big data, data has become an important strategic resource for social development. However, with the increasing complexity of the network environment, privacy leakage and malicious attacks emerge in an endless stream. As a new data sharing model, federated learning can share data on the premise of protecting data privacy. In particular, it can effectively solve the shortcomings of traditional intrusion detection model. Therefore, this paper proposed an intrusion detection mechanism based on federated learning. This paper first introduced the structure and characteristics of federated learning and intrusion detection model, And deeply analyzed the feasibility of intrusion detection mechanism based on federated learning to effectively improve the detection accuracy and efficiency. The prototype system was developed through the requirement analysis and design of the model, and the simulation experimented with function programming. It is found that the federated learning mechanism can realize the sharing of multi-party attack logs on the premise of ensuring the data privacy security of participating clients. At the same time, through the control experiments of multiple groups of control variables, it is proved that the intrusion detection mechanism based on federated learning has significantly improved the detection accuracy and efficiency.更多还原