Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection

Federated Learning (FL) is a promising form of distributed machine learning that preserves privacy by training models locally without sharing raw data. While FL ensures data privacy through collaborative learning, it faces several critical challenges. These include vulnerabilities to reverse engineering, risks to model architecture privacy, susceptibility to model poisoning attacks, threats to data integrity, and the high costs associated with communication and connectivity. This paper presents a comprehensive review of FL, categorizing data partitioning formats into horizontal federated learning, vertical federated learning, and federated transfer learning. Furthermore, it explores the integration of FL with blockchain, leveraging blockchain’s decentralized nature to enhance FL’s security, reliability, and performance. The study reviews existing FL models, identifying key challenges such as privacy risks, communication overhead, model poisoning vulnerabilities, and ethical dilemmas. It evaluates privacy-preserving mechanisms and security strategies in FL, particularly those enabled by blockchain, such as cryptographic methods, decentralized consensus protocols, and tamper-proof data logging. Additionally, the research analyzes regulatory and ethical considerations for adopting blockchain-based FL solutions. Key findings highlight the effectiveness of blockchain in addressing FL challenges, particularly in mitigating model poisoning, ensuring data integrity, and reducing communication costs. The paper concludes with future directions for integrating blockchain and FL, emphasizing areas such as interoperability, lightweight consensus mechanisms, and regulatory compliance.

Federated learning (FL) represents a transformative shift in machine learning, moving from conventional centralized approaches to a distributed framework that emphasizes data privacy and security. The FL server transmits an initial model to clients, which they train locally on their private data. After training, the server aggregates model updates from each client to update the global model. Selecting the best clients in FL is critical to improving the convergence speed and accuracy of the final model, which requires careful client selection approaches. The client selection phase of FL faces numerous challenges that impact overall training performance, including statistical heterogeneity and system heterogeneity resulting from the diversity of client data and resources. Communication costs present another challenge, especially in networks with limited client communication resources. Additionally, selecting trustworthy clients represents another challenge, as selecting malicious clients creates a significant risk within the FL training process. Moreover, the fairness challenge entails providing fair opportunities for all clients to participate in training. To address these challenges, we offer solutions that utilize effective techniques, approaches, and client selection methods. This survey presents a taxonomy of modern client selection methods in FL, highlighting the improvements in FL performance and effectiveness achieved through these methods, including greedy selection, reinforcement learning-based selection, multi-armed bandit-based selection, clustering-based selection, and reputation & security-based selection. Subsequently, it offers a general comparison between these methods in terms of their core ideas, advantages, limitations, and use cases. Finally, future and potential trends in client selection and improving performance in FL are identified.

Federated learning (FL) enables privacy-preserving distributed machine learning by training models on edge client devices using their local data without revealing their raw data. In edge environments, various applications require different neural network models, making it crucial to perform joint training of multiple models on edge devices, known as multi-task FL. While existing multi-task FL approaches enhance resource utilization on edge devices through adaptive resource configuration or client selection, optimizing either of these aspects alone may lead to suboptimality. Therefore, in this paper, we explore a joint client selection and resource configuration method called JCSRC for multi-task FL, aiming to maximize energy efficiency in environments with limited computation and communication resources and heterogeneous client devices. Firstly, we formalize this problem as a mixed-integer nonlinear programming problem considering all these characteristics and prove its NP-hardness. To address this problem, we first design a multi-agent reinforcement learning (MARL)-based client selection method that selects appropriate clients for each task to train their models. The MARL method makes client selection decisions based on the clients’ data quality, energy efficiency, communication, and computation capacity to ensure fast convergence and energy efficiency. Then, we design a particle swarm optimization (PSO)-based resource configuration scheme that configures appropriate computation and bandwidth resources for each task on each client. The PSO scheme makes resource configuration decisions based on theoretically derived optimal CPU frequency and bandwidth to achieve high energy efficiency. Finally, we carry out extensive simulations and testbed-based experiments to validate our proposed JCSRC. The results demonstrate that, in comparison to state-of-the-art solutions, JCSRC can save energy consumption by up to 59% to achieve the target accuracy.

Federated Learning (FL) is a revolutionary distributed machine learning paradigm in which collaborative model training on decentralized devices is achieved without sharing raw data. However, FL is susceptible to poisoning attacks and model update-based leakage of privacy through exchange. We propose in this paper a secure FL framework with encryption based methods to ensure confidentiality and integrity of model updates on sending and aggregation. We compare the application of two cryptographic methods: Symmetric Encryption to offer lightweight, efficient security and Homomorphic Encryption (HE) for advanced privacy-preserving computation on encrypted data. We conduct extensive experiments to assess the trade-offs in security, performance, and accuracy. We find that symmetric encryption offers robust protection with low runtime overhead, and HE offers maximum security assurances at the expense of computational complexity. To evaluate their impact, we conduct simulation-based experiments on the MNIST dataset using the FedAvg aggregation algorithm under a cyclic label flipping attack, a form of data poisoning. This work aims to objectively explore how encryption affects federated learning and evaluates its significance in maintaining data privacy and efficient model performance.

False Data Injection Attacks (FDIAs) pose a substantial risk to the reliability and stability of Cyber-Physical Power Systems (CPPS). While federated learning (FL) has emerged as a promising approach to detect such attacks without exposing sensitive data, security concerns remain in FL, including untrusted central aggregators and potential malicious client updates. This research integrate a private Ethereum blockchain layer and homomorphic encryption into a secure FL framework for FDIA detection to verify model updates and authenticate participating nodes. We design smart contracts to immutably log model update hashes and enforce client authentication, enhancing traceability and tamper-resistance. A prototype implementation uses Ethereum smart contracts for model update verification and client identity management. We simulate the blockchain-integrated FL on a cyber-physical power system dataset using three detection models – XGBoost, LSTM, and a Transformer – and analyze the blockchain-induced latency and communication overhead under a specific network configuration. Results show that the blockchain layer has negligible impact on detection accuracy (global AUC ∼ 0.94-0.96 across models) while introducing a moderate training time overhead (∼ 13–40% increase in training duration due to block confirmation delays). The proposed research demonstrates a viable approach to blockchain-aided federated learning for critical infrastructure security, combining data privacy, model integrity, and participant trust in a unified framework.

Federated Learning (FL) has gained significant attention as a distributed machine learning paradigm, leveraging edge clients for collaborative training while preserving data privacy. However, statistical heterogeneity, arising from diverse client data distributions, poses a significant challenge to FL performance. In this work, we propose a novel heterogeneity-aware client selection scheme based on prototype margin to mitigate these challenges. By utilizing prototype learning, we capture effective data representations, allowing client selection to better account for both data quality and distribution. The proposed scheme is designed for practical wireless communication networks, where clients are clustered and we select participants based on joint prototype margin and wireless channel. To further optimize the training process, we jointly optimize client selection and bandwidth allocation, accounting for dynamic network conditions and heterogeneous client capabilities. Experimental results demonstrate that our approach significantly improves model accuracy and reduces communication overhead.

As federated learning (FL) keeps dominating the way in privacy-preserving machine learning (ML), notably in finance, its long-term sustainability is confronted with the approaching challenge of quantum computing. The introduction of quantum computing poses a challenge to traditional cryptographic technique on which FL relies RSA, elliptic curve cryptography (ECC), and some homomorphic encryption (HE) methods applied for encrypting model updates during training rendering this chapter to explore the interplay between the threat of quantum computing and the FL architectures, with emphasis on the implications this interaction introduces to cybersecurity and privacy in finance applications. Quantum computers are theoretically capable of solving hard math problems that have been regarded as computationally intractable for quantum computers. The well-known algorithms like Shor’s and Grover’s provides serious risk to the cryptographic procedures FL pipelines depends on. The finance sector, by its nature involving sensitive data and dependence on secure, distributed ML systems, is particularly vulnerable. The chapter begins by summarizing the fundamentals of FL and current encryption methods adapted to protect FL workflows. It then shifts towards the essence of quantum computing, emphasizing on the notable algorithms that threaten FL. We also explore potential attack points through which quantum computing could attack FL, e.g., model inversion attacks, poisoning attacks facilitated by quantum capabilities, and threats to secure aggregation. Post-quantum cryptography (PQC) is also presented as a potential counterattack, followed by a discussion of its use case in FL platforms. This chapter attempts to close the gap between FL and quantum computing threats to the financial sector. It is an introduction to practitioners and researchers to revisit examining security assumptions in FL and move towards the quantum-augmented cyber threat model.

In recent years, to surmount the challenges of data sensitivity and data silos, federated learning (FL), a collaborative decentralized privacy preservation machine learning framework was proposed and rapidly became a current research hotspot. In this paper, we present an overview of FL workflow, as well as the communication overhead and privacy leakage problems associated with FL. In order to alleviate these two pain points, several corresponding solutions are presented in this paper along with their advantages and disadvantages. To reduce the communication overhead, this paper suggests three reliable approaches by reviewing related research including increasing the amount of computing on the edge side, model compression, and improving parallelism. To address the privacy concerns, this paper introduces three prevailing privacy preservation techniques: differential privacy, homomorphic encryption, and secure multiparty computation (SMC), and shows how to efficiently incorporate these privacy-preserving techniques into a federated learning framework by summarizing relevant literature. On the whole, this paper contributes to explaining the overall workflow of a FL framework and helps advance the understanding of FL in improving communication efficiency and enhancing privacy security.

FedHEONN: Federated and homomorphically encrypted learning method for one-layer neural networks

Federated Learning (FL) has shown great potential as a privacy-preserving solution to training a centralized model based on local data from available clients. However, we argue that, over the course of training, the available clients may exhibit some volatility in terms of the client population, client data, and training status. Considering these volatilities, we propose a new learning scenario termed volatile federated learning (Volatile FL) featuring set volatility, statistical volatility, and training volatility. The volatile client set along with the dynamic of clients’ data and the unreliable nature of clients (e.g., unintentional shutdown and network instability) greatly increase the difficulty of client selection. In this paper, we formulate and decompose the global problem into two sub-problems based on alternating minimization. For an efficient settlement for the proposed selection problem, we quantify the impact of clients’ data and resource heterogeneity for Volatile FL and introduce the cumulative effective participation data as an optimization objective. Based on this, we propose Upper Confidence Bound based Greedy Selection, dubbed UCB-GS, to address the client selection problem in volatile FL. Theoretically, we prove that the regret of UCB-GS is strictly bounded by a finite constant, justifying its theoretical feasibility. Furthermore, experimental results show that our method significantly reduces the number of training rounds (by up to 62%) while increasing the global model’s accuracy by 7.51%.
\n

Federated Learning (FL) is a new paradigm in distributed machine learning that allows numerous participants to train a common model without exchanging raw data. This strategy improves data privacy and security, addressing major concerns in sensitive domains including healthcare, banking, and mobile applications. Unlike traditional centralized learning, FL moves model training closer to the data source, reducing data leakage risks and boosting regulatory compliance (e.g., GDPR, HIPAA). This paper provides a complete overview of federated learning, including its core architecture, distinct types (horizontal, vertical, and transfer learning), enabling technologies (such as secure multiparty computation, differential privacy, and homomorphic encryption), and real-world applications. The paper also examines the fundamental issues encountered by FL, such as data heterogeneity, communication overhead, and vulnerability to adversarial assaults. The report concludes with interesting research prospects for increasing model performance, security, and scalability in federated environments.

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively ``breaks the direct connection'' between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL.

Utilizing the federated learning (FL) technique, data owners can collaboratively train artificial intelligence models, retaining all training data on their premises to minimize the potential for personal data breaches. However, self-interested users (e.g., free riders) bring new challenges that hinder the development of FL techniques. To this end, we propose a two-stage client selection scheme comprising a multiarmed bandit (MAB)-based candidate client selection method and an auction-based training client selection method. Specifically, our client selection scheme initially formulates the FL system into an MAB system, where clients are the arms and the server is the player. Then, we quantify the similarity between a local model and the server side, which is the designed metric for model aggregation and reward computation updating based on the fuzzy mathematical strategy. Next, based on the Thompson Sampling strategy, the server can intelligently determine the reward of each client, and clients with more significant rewards have the chance for local model training. With an auction method, the server can determine the training clients to reduce the training cost while maximizing each client’s revenue. Extensive experiments on real-world data sets demonstrate that the proposed scheme outperforms representative FL schemes (i.e., FedAvg, FedProx, FedMax, and MFL) regarding the model’s convergence rate and cost in FL systems with free riders.

Cross-silo federated learning (FL) is a privacypreserving distributed machine learning where organizations acting as clients cooperatively train a global model without uploading their raw local data. Recently, the cross-silo FL in multi-access edge computing (MEC) is used in increasing industrial applications. Most existing research on cross-silo FL pays attention to the performance aspect, ignoring the incentive mechanism for high-quality client selection and long participation in model training for efficient and stable FL, which has prevented the widespread adoption of cross-silo FL in MEC. In this paper, we propose an incentiVe mechanism with QuAlity-Aware and Reputation-Aware based on the infinitely repeated game for cross-silo FL named VARF. VARF selects high-quality and highreputation edge nodes (ENs) as candidates for model training in the cross-silo FL by a heuristic algorithm and then motivates the selected ENs to actively contribute their resources. VARF also models the long-term behavior of ENs in cross-silo FL as an infinitely repeated game and derives a stable and long-term cooperative strategy for clients while maximizing the amount of local data for model learning in cross-silo FL. Extensive simulations with real-world datasets demonstrate that the performance of VARF is more beneficial than other benchmarks. Meanwhile, experimental results show that cloud platforms (CPs) and ENs eventually form a long and stable cooperative relationship under the trigger strategy.

Federated learning (FL) unleashes the full potential of training a global statistical model collaboratively from edge clients. In wireless FL, for the scarcity of spectrum, only a fraction of clients are capable to participate in the FL training in each round. On the other hand, the performance of FL suffers from the label noise, which naturally exists in the dataset of each client. To alleviate the label noise issue, prior works proposed several client selection algorithms, where the privacy of raw data might be compromised when extra information exchange was introduced. To avoid extra information exchange in FL, we propose to leverage an algorithm that measures the noise ratio of each client based on a clean validation dataset. We then propose an online client selection framework, supported by Copeland score and multi-arm bandits, which can select the client set with low noise ratios efficiently. The proposed algorithm is performed in the server side, thereby it can be implemented in the basic FL framework seamlessly. Simulation results demonstrate that our proposed algorithm spends less training time while guaranteeing the required accuracy compared to other baseline algorithms.