Outsourcing logistic regression classification services to the cloud is highly beneficial for streaming data. However, it raises critical privacy concerns for the input data and the training models. Current solutions for encrypted logistic regression classification fall short in the processing of encrypted streaming data. In this paper, we propose a privacy-preserving logistic regression model (PrivESD), which allows computation over encrypted streaming data. First, we propose a lightweight framework, which creates a collaborative workload between the cloud and the edge thereby reducing the computation complexity of the cloud and the number of communications between the data owners and the cloud. Second, we develop a tailored building block library with strong data confidentiality that supports comparison operations. This library has then been used to construct logistic regression. Finally, we devise a processing scheme that uses stochastic gradient descent with momentum to train the model to prevent the problem of local optimal convergence with streaming data. We have conducted extensive performance analysis demonstrating that the proposed protocols such as our secure compare protocol outperforms existing schemes such as Bost [44] and Guo [45], and that the encryption and decryption operations of PrivESD are similar to that of Paillier [42] with$2^{30}$keys.

With the recent rapid expansion of the smart grid infrastructure paving the way for greater integration of computer and network technologies within the power grid, it has become well suited for the application of machine learning techniques. However, machine learning requires vast amounts of data, which within the smart grid setting can reveal great amounts of personal details of the individuals using the grid. This work considers the application of a variant of distributed machine learning, federated learning, which enhances data privacy. We propose a Smart Grid Hierarchical Federated Learning (SGHFL) framework, which is tuned to common smart grid architectures in the real world. We demonstrate how our SGHFL framework improves client dropout and poisoning robustness, using relatively lightweight models suitable for devices with limited computational capability. We provide theoretical justification underlying our design and have evaluated our algorithms and framework with three datasets/environments of progressively increasing practicality. We have also compared our framework with relevant works.

With the increasing tension between conflicting requirements of the availability of large amounts of data for effective machine learning-based analysis, and for ensuring their privacy, the paradigm of federated learning has emerged, a distributed machine learning setting where the clients provide only the machine learning model updates to the server rather than the actual data for decision making. However, the distributed nature of federated learning raises specific challenges related to fairness in a heterogeneous setting. This motivates the focus of our article, on the heterogeneity of client devices having different computational capabilities and their impact on fairness in federated learning. Furthermore, our aim is to achieve fairness in heterogeneity while ensuring privacy. As far as we are aware there are no existing works that address all three aspects of fairness, device heterogeneity, and privacy simultaneously in federated learning. In this article, we propose a novel federated learning algorithm with personalization in the context of heterogeneous devices while maintaining compatibility with the gradient privacy preservation techniques of secure aggregation. We analyze the proposed federated learning algorithm under different environments with different datasets and show that it achieves performance close to or greater than the state-of-the-art in heterogeneous device personalized federated learning. We also provide theoretical proofs for the fairness and convergence properties of our proposed algorithm.

Trust management systems (TMSs) play an important role in Internet of Things (IoT) by providing a means of finding whether a given device can provide a service to a satisfactory level, and for identifying potentially malicious devices in the network. Context awareness extends trust models by allowing a trustor to filter and aggregate evidence by their relevance to the current situation. Context awareness is important in the formulation of trust in IoT networks due to their heterogeneity and due to the dynamic changes in the capabilities of IoT devices. In this article, we have proposed a new type of attack on context-aware trust models for IoT systems, context-based attacks. In this attack, an adversary manipulates the context to impact a target group of IoT devices, while other devices in nontargeted groups are not even aware of the attack. We have demonstrated the effectiveness of this new type of attack on seven previously proposed trust models through practical simulations and theoretical proofs. This article also proposes a new TMS that can mitigate such context-based attacks.

The susceptibility of federated learning (FL) to attacks from untrustworthy endpoints has led to the design of several defense systems. FL defense systems enhance the federated optimization algorithm using anomaly detection, scaling the updates from endpoints depending on their anomalous behavior. However, the defense systems themselves may be exploited by the endpoints with more sophisticated attacks. First, this paper proposes three categories of attacks and shows that they can effectively deceive some well-known FL defense systems. In the first two categories, referred to as on-off attacks, the adversary toggles between being honest and engaging in attacks. We analyse two such on-off attacks, label flipping and free riding, and show their impact against existing FL defense systems. As a third category, we propose attacks based on “good mouthing” and “bad mouthing”, to boost or diminish influence of the victim endpoints on the global model. Secondly, we propose a new federated optimization algorithm, Viceroy, that can successfully mitigate all the proposed attacks. The proposed attacks and the mitigation strategy have been tested on a number of different experiments establishing their effectiveness in comparison with other contemporary methods. The proposed algorithm has also been made available as open source. Finally, in the appendices, we provide an induction proof for the on-off model poisoning attack, and the proof of convergence and adversarial tolerance for the new federated optimization algorithm.