Distributed Fault Detection Based on Credibility and Cooperation for WSNs in Smart Grids.

Due to the increasingly important role in monitoring and data collection that sensors play, accurate and timely fault detection is a key issue for wireless sensor networks (WSNs) in smart grids. This paper presents a novel distributed fault detection mechanism for WSNs based on credibility and cooperation. Firstly, a reasonable credibility model of a sensor is established to identify any suspicious status of the sensor according to its own temporal data correlation. Based on the credibility model, the suspicious sensor is then chosen to launch fault diagnosis requests. Secondly, the sending time of fault diagnosis request is discussed to avoid the transmission overhead brought about by unnecessary diagnosis requests and improve the efficiency of fault detection based on neighbor cooperation. The diagnosis reply of a neighbor sensor is analyzed according to its own status. Finally, to further improve the accuracy of fault detection, the diagnosis results of neighbors are divided into several classifications to judge the fault status of the sensors which launch the fault diagnosis requests. Simulation results show that this novel mechanism can achieve high fault detection ratio with a small number of fault diagnoses and low data congestion probability.

WFB: watermarking-based copyright protection framework for federated learning model via blockchain.

Federated learning (FL) enables users to train the global model cooperatively without exposing their private data across the engaged parties, which is widely used in privacy-sensitive business. However, during the life cycle of FL models, both adversaries' attacks and ownership generalization threaten the FL models' copyright and affect the models' reliability. To address these problems, existing model watermarking techniques can be used to verify FL model's ownership. However, due to the lack of credible binding from "model extracted watermarks" to "ownership verification", it is difficult to form a closed-loop watermarking framework for copyright protection. Therefore, starting from the shortcomings of the current watermark verification scheme, this article proposed WFB, a blockchain-empowered watermarking framework for ownership verification of federated models. Firstly, we propose a improved watermark generation algorithm to solve the credibility issue of watermarks. Secondly, we propose a watermark embedding method in federated learning, while blockchain technology is used to ensure the credible storage of watermark information throughout the process. Thirdly, the credibility of ownership verification is improved because of the watermark authenticity. Experimental results demonstrate the fidelity, effectiveness and robustness of WFB, with other superiorities such as improving process security and traceability.