基于GB-AEnet-FL网络的物联网设备异常检测

针对物联网场景下，传统异常检测方法在海量不均衡数据中检测准确率低、数据异构导致模型泛化能力差等问题，提出了基于联邦学习的对抗双编码异常检测网络 （GB-AEnet-FL）的物联网设备异常检测算法。首先，提出了一种基于异常数据的主动特征分布学习算法，主动学习数据的潜在特征分布，通过数据重构扩充异常数据，均衡正负样本比例。其次，在潜在特征层引入了对抗训练机制并添加一致性增强约束和收缩约束，提高特征提取的精度。最后，设计了一种基于动态模型选择的联邦学习算法，比较局部模型与全局模型的置信度评分，动态选择部分联邦体参与，加速模型的聚合，在一定程度上也保护了用户隐私。在四个不同数据集上进行验证，结果显示，所提算法在检测准确度优于传统算法，且泛化能力得到相应提升。

Anomaly detection algorithm of IoT devices based on GB-AEnet-FL network

Aiming at the problems of low detection accuracy in massive unbalanced data and poor model generalization ability caused by data heterogeneity in traditional anomaly detection methods in IoT scenarios, this paper proposed an adversarial dual-coding anomaly detection network based on federated learning(GB-AEnet-FL). Firstly, this paper proposed an active feature distribution learning algorithm based on abnormal data, which actively learnt the potential feature distribution of data, expanded abnormal data through data reconstruction, and balanced the proportion of positive and negative samples. Secondly, this paper introduced an adversarial training mechanism in the latent feature layer adding consistency enhancement constraints and shrinkage constraints to improve the accuracy of feature extraction. Finally, this paper designed a federated learning algorithm based on dynamic model selection which compared the confidence scores of the local model and the global model, dynamically selected part of the federated bodies to participate, accelerated the aggregation of models, and protected user privacy to a certain extent. Validated on four different datasets, the results show that the proposed algorithm is better than the traditional algorithm in detection accuracy, and the generalization ability is improved accordingly.