Currently, most anomaly detection approaches in industrial control systems (ICSs) use network event logs to build models, and current unsupervised machine learning methods rarely use spatiotemporal correlations and other dependencies between multiple variables (sensors/actuators) in a system to detect anomalies. Most of the existing anomaly detection technologies simply compare the current states with the predicted normal range. Due to the highly dynamic characteristic of industrial control systems, it is insufficient to simply compare the current states with the predicted normal range. As a result, these approaches have low detection rates for unknown or new types of attacks. In view of these shortcomings, this paper presents a network model for predicting sensor/controller parameters in industrial control systems. To predict the parameter values of the sensors and controllers more accurately, the 1D convolutional neural network (1D_CNN) and gated recurrent unit (GRU) are combined to fully learn the spatiotemporal correlation and other dependencies between the parameter values of the sensors and controllers at each moment. An abnormal state detection method based on the calculation of the statistical deviation is proposed to realize the anomaly detection of industrial control systems. The model is validated on the Secure Water Treatment (SWaT) dataset. The precision, recall and F1 scores are used to evaluate the effectiveness of this method in anomaly detection on the SWaT dataset. The experimental results show that the average precision and recall of this method are 0.99 and 0.85, respectively, and that the average F1 score is 0.91. The experimental results show that the proposed method can be successfully applied to anomaly detection systems in industrial control systems with lower false positive rates.
28 January 2025 in IEEE Internet of Things Journal
With the rapid advancement of wearable devices and IoT technologies, sensor data generated by edge devices has surged. This data is crucial for advancing IoT applications, including health status monitoring, abnormal behavior detection, and environmental monitoring. However, traditional centralized learning requires uploading data to a central server, raising security and privacy concerns and hindering data application. Federated learning (FL) offers a solution by enabling collaborative model training on IoT devices without transferring data from the local device. In practice, edge devices generate data that is often highly heterogeneous, making it challenging for the global FL model to capture local data distributions accurately, leading to significant performance degradation. Additionally, imbalanced edge device resources and limited bandwidth can cause data transmission delays or interruptions, impacting application feasibility. To address these issues, we propose PFedKD, a novel personalized FL algorithm based on knowledge distillation, aimed at enhancing the model’s generalization ability and reducing communication overhead in heterogeneous IoT data environments. PFedKD constructs a public dataset using unlabeled pseudo data to extract knowledge from each client, training personalized models that fit local data distributions. This method controls dataset size while enhancing performance. During communication, only logits and class prototypes are transmitted, ensuring high communication efficiency. Sharpness Aware Minimization is introduced in local model training to optimize generalization. Additionally, we design a weight distribution mechanism based on client sample quality evaluation that optimizes knowledge aggregation and model personalization. Extensive experiments demonstrate that PFedKD significantly outperforms state-of-the-art baselines in both learning performance and communication efficiency.
In cooperative intelligent transportation systems (CITS), federated learning enables vehicles to train a global model without sharing private data. However, the lack of an unlearning mechanism to remove the influence of vehicle-specified data from the global model potentially violates data protection regulations regarding the right to be forgotten. While the existing federated unlearning (FU) methods exhibit promising unlearning effects, their practicality in CITS is hindered due to the time-consuming retraining steps required by other vehicles and the non-negligible performance sacrifice on the un-forgotten data. Therefore, achieving effective unlearning without extensive retraining, while minimizing performance degradation on the un-forgotten data remains a challenge. In this work, we propose FedEditor, an efficient and effective FU framework in CITS that addresses the above challenge by reconfiguring the global model’s representation space to remove critical classification-related knowledge from the unlearned data. Firstly, FedEditor enables vehicles to perform the unlearning process locally on the global model, eliminating the participation of other vehicles and improving efficiency. Secondly, FedEditor captures and aligns the representations of the unlearned data with those of the nearest incorrect class centroid derived from non-training data, ensuring effective unlearning while preserving the un-forgotten data’s knowledge relatively intact for achieving competitive model performance. Finally, FedEditor refines the global model’s output distributions using the vehicles’ remaining data and incorporates a drift-mitigating regularization term, minimizing the negative impact of unlearning operations on model performance. Experimental results show that FedEditor reduces the unlearning rate by up to 99.64% without time-consuming retraining, while limiting the predictive performance loss of the resulting global model to less than 3.88% across five models and seven datasets.
18 May 2020 in EURASIP Journal on Wireless Communications and Networking
Due to the complexity of industrial control systems and the diversity of protocols in networks, it is difficult to build intrusion detection models based on network characteristics and physical modeling. In order to build a better flow model without additional knowledge, we propose an intrusion detection method based on the content of network packets. The construction of the model is based on the idea of ZOE method. The similarity between flows is calculated through the sequential coverage algorithm, the normal flow model is established by multi-layered clustering algorithm, and the Count-Mean-Min Sketch is used to store and count the flow model. By comparing the unknown flow with the constructed normal flow model, we achieve the intrusion detection of industrial control system (ICS). The overall experimental results on 4 ICS datasets show that the improved method can effectively improve the detection rate and reduce the false-positive rate. The detection rate reached 96.7% on average, and the false-positive rate reached 0.7% on average.
28 April 2020 in Concurrency and Computation: Practice and Experience