Federated learning (FL) offers innovative solutions for privacy-preserving distributed machine learning (ML). Different from centralized data collection algorithms, FL enables participants to locally train their model and only share the model updates for aggregation. Since private data never leaves the end node, FL effectively mitigates privacy leakage during collaborative training. Despite its promising potential, FL is vulnerable to various attacks due to its distributed nature, affecting the entire life cycle of FL services. These threats can harm the model’s utility or compromise participants’ privacy, either directly or indirectly. In response, numerous defense frameworks have been proposed, demonstrating effectiveness in specific settings and scenarios. To provide a clear understanding of the current research landscape, this article reviews the most representative and state-of-the-art threats and defense frameworks throughout the FL service life cycle. We start by identifying FL threats that harm utility and privacy, including those with potential or direct impacts. Then, we dive into the defense frameworks, analyze the relationship between threats and defenses, and compare the trade-offs among different defense strategies. We subsequently revisit these studies to evaluate their practicality in real-world scenarios and conclude by summarizing existing research bottlenecks and outlining future directions. We hope this survey sheds light on trustworthy FL research and contributes to the FL community.

In the current smart grid, managing high-energy consumption loads, particularly electric vehicles (EVs), become increasingly complex. This paper introduces a framework that employs non-intrusive load monitoring (NILM) techniques for enhanced energy management in smart grids. Our approach encompasses a broader range of common flexible loads and energy related to EV charging. The NILM technology enables the detailed analysis of individual appliance consumption patterns from aggregated smart meter data, addressing privacy concerns and technical limitations. In detail, we propose a new NILM algorithm, Serial Multi-task Transformer with Attention (SMTA), to address the problem of long-term household load disaggregation. SMTA uses a Serial-Correlation mechanism with period-based dependencies and cyclical information aggregation for effective period time series analysis and utilizes the Task-Specific Attention strategy to find the power influence between appliances. Afterwards, based on the NILM results, we develop an energy management model aiming to optimize the net operation cost in the smart grid, after all active customers participation in ancillary service programs. The proposed framework has been verified on a modified IEEE 57-bus radial distribution system based on real-world household data. The results show that the SMTA algorithm significantly improves load disaggregation accuracy. Furthermore, the proposed framework in comparison to basic energy management. reduces the net operation costs by up to 26.9%, highlighting the substantial economic benefits of integrating NILM into smart grid operations.

Semi-supervised learning (SSL) is a popular research area in machine learning which utilizes both labeled and unlabeled data. As an important method for the generation of artificial hard labels for unlabeled data, the pseudo-labeling method is introduced by applying a high and fixed threshold in most state-of-the-art SSL models. However, early models prefer certain classes that are easy to learn, which results in a high-skewed class imbalance in the generated hard labels. The class imbalance will lead to less effective learning of other minority classes and slower convergence for the training model. The aim of this paper is to mitigate the performance degradation caused by class imbalance and gradually reduce the class imbalance in the unsupervised part. To achieve this objective, we propose FocalMatch, a novel SSL method that combines FixMatch and focal loss. Our contribution of FocalMatch adjusts the loss weight of various data depending on how well their predictions match up with their pseudo labels, which can accelerate system learning and model convergence and achieve state-of-the-art performance on several semi-supervised learning benchmarks. Particularly, its effectiveness is demonstrated with the dataset that has extremely limited labeled data.

With the widespread use of end devices, online multi-label learning has become popular as the data generated by users using the Internet of Things devices have become huge and rapidly updated. However, in many scenarios, the user data are often generated in a geographically distributed manner that is often inefficient and difficult to centralize for training machine learning models. At the same time, current mainstream distributed learning algorithms always require a centralized server to aggregate data from distributed nodes, which inevitably causes risks to the privacy of users. To overcome this issue, we propose a distributed approach for multi-label classification, which trains the models in distributed computing nodes without sharing the source data from each node. In our proposed method, each node trains its model with its local online data while it also learns from the neighbour nodes without transferring the training data. As a result, our proposed method achieved the online distributed approach for multi-label classification without losing performance when taking existing centralized algorithms as a reference. Experiments show that our algorithm outperforms the centralized online multi-label classification algorithm in F1 score, being 0.0776 higher in macro F1 score and 0.1471 higher for micro F1 score on average. However, for the Hamming loss, both algorithms beat each other on some datasets, and our proposed algorithm loses 0.005 compared to the centralized approach on average, which can be neglected. Furthermore, the size of the network and the degree of connectivity are not factors that affect the performance of this distributed online multi-label learning algorithm.