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.

Magnetic Resonance Imaging (MRI) excels in medical diagnostics with its superior soft tissue contrast and detailed anatomical visualization, providing critical support for precise medical image segmentation. However, traditional full K-space sampling is time-consuming, limiting efficiency in clinical settings. To address this challenge, we propose a novel method leveraging Reinforcement Learning (RL) to adaptively sample K-space, optimizing both MRI acquisition efficiency and segmentation accuracy. Our approach features an RL-driven policy network that strategically selects the most informative K-space samples, substantially reducing scan times while maintaining critical anatomical details. By integrating segmentation performance into the reward model, our method directly aligns the sampling process with accurate pathological segmentation. Furthermore, sparse K-space data are reconstructed into high-quality images, ensuring precise inputs for segmentation networks. Experiments on ACDC, AMOS, M&Ms-2, CHAOS and MSD datasets demonstrate that our approach not only accelerates MRI processing but also significantly enhances segmentation accuracy, showcasing its potential for clinical applications where speed and precision are paramount.

A large number of federated learning (FL) algorithms have been proposed for different applications and from varying perspectives. However, the evaluation of such approaches often relies on a single metric (e.g., accuracy). Such a practice fails to account for the unique demands and diverse requirements of different use cases. Thus, how to comprehensively evaluate an FL algorithm and determine the most suitable candidate for a designated use case remains an open question. To mitigate this research gap, we introduce the Holistic Evaluation Metrics (HEM) for FL in this work. Specifically, we collectively focus on three primary use cases, which are Internet of Things (IoT), smart devices, and institutions. The evaluation metric encompasses various aspects including accuracy, convergence, computational efficiency, fairness, and personalization. We then assign a respective importance vector for each use case, reflecting their distinct performance requirements and priorities. The HEM index is finally generated by integrating these metric components with their respective importance vectors. Through evaluating different FL algorithms in these three prevalent use cases, our experimental results demonstrate that HEM can effectively assess and identify the FL algorithms best suited to particular scenarios. We anticipate this work sheds light on the evaluation process for pragmatic FL algorithms in real-world applications.