The fast proliferation of edge computing devices brings an increasing growth of data, which directly promotes machine learning (ML) technology development. However, privacy issues during data collection for ML tasks raise extensive concerns. To solve this issue, synchronous federated learning (FL) is proposed, which enables the central servers and end devices to maintain the same ML models by only exchanging model parameters. However, the diversity of computing power and data sizes leads to a significant difference in local training data consumption, and thereby causes the inefficiency of FL. Besides, the centralized processing of FL is vulnerable to single-point failure and poisoning attacks. Motivated by this, we propose an innovative method, federated learning with asynchronous convergence (FedAC) considering a staleness coefficient, while using a blockchain network instead of the classic central server to aggregate the global model. It avoids real-world issues such as interruption by abnormal local device training failure, dedicated attacks, etc. By comparing with the baseline models, we implement the proposed method on a real-world dataset, MNIST, and achieve accuracy rates of 98.96% and 95.84% in both horizontal and vertical FL modes, respectively. Extensive evaluation results show that FedAC outperforms most existing models.

The booming of edge computing enables and reshapes this big data era. However, privacy issues arise because increasing volume of data are published per second while the edge devices can only provide limited computing and storage resources. In addition, this has been aggravated by new emerging features of edge computing, such as decentralized and hierarchical infrastructure, mobility, and content-aware applications. Although some existing privacy-preserving methods are extended to this domain, the privacy issues of data dissemination between multiple edge nodes and end-users are barely studied. Motivated by this, we propose a dynamic customizable privacy-preserving model based on Markov decision process to obtain the optimized trade-off between customizable privacy protection and data utility. We start with establishing a game model between users and adversaries based on a QoS-based payoff function. A modified reinforcement learning algorithm is deployed to derive the exclusive Nash Equilibrium. Furthermore, the model can achieve fast convergence by the reduction of cardinality from n to 2. Extensive experimental results confirm the significance of the proposed model comparing to the existing work both in terms of effectiveness and feasibility.

Fog computing faces various security and privacy threats. Internet of Things (IoTs) devices have limited computing, storage, and other resources. They are vulnerable to attack by adversaries. Although the existing privacy-preserving solutions in fog computing can be migrated to address some privacy issues, specific privacy challenges still exist because of the unique features of fog computing, such as the decentralized and hierarchical infrastructure, mobility, location and content-aware applications. Unfortunately, privacy-preserving issues and resources in fog computing have not been systematically identified, especially the privacy preservation in multiple fog node communication with end users. In this paper, we propose a dynamic MDP-based privacy-preserving model in zero-sum game to identify the efficiency of the privacy loss and payoff changes to preserve sensitive content in a fog computing environment. First, we develop a new dynamic model with MDP-based comprehensive algorithms. Then, extensive experimental results identify the significance of the proposed model compared with others in more effectively and feasibly solving the discussed issues.