Federated Learning Systems Research Articles

Interpreting Federated Learning (FL) Models on Edge Devices by Enhancing Model Explainability with Computational Geometry and Advanced Database Architectures

Federated learning (FL) on edge devices has emerged as a promising approach for decentralized model training, enabling data privacy and efficiency in distributed networks. However, the complexity of these models presents significant challenges in terms of transparency and interpretability, which are critical for trust and accountability in real-world applications. This paper explores the integration of explainable AI techniques to enhance model interpretability within federated learning systems. By incorporating computational geometry, we aim to optimize model structure and decision-making processes, providing clearer insights into how models generate predictions. Additionally, we examine the role of advanced database architectures in managing the complexity of federated learning models on edge devices, ensuring efficient data handling and storage. Together, these approaches contribute to a more transparent, efficient, and scalable framework for federated learning on edge networks, addressing key challenges in both model explainability and performance optimization. This review highlights recent advancements and suggests future directions for research at the intersection of federated learning (FL), edge computing, explainability, and computational techniques.

SecDefender: Detecting low-quality models in multidomain federated learning systems

Federated learning (FL) is an innovative distributed learning paradigm that permits multiple parties to train models collaboratively while protecting individual privacy. However, it encounters security challenges, making it vulnerable to several adversarial attacks and leading to compromising model performance. Existing research on FL poisoning attacks and defense techniques tends to be application-specific, primarily emphasizing attack capabilities. However, it fails to consider inherent vulnerabilities in FL and the impact of attack intensity. To our knowledge, no existing work has delved into these issues within a multi-domain FL environment. This paper addresses these concerns by investigating the consequences of targeted label-flipping attacks within FL systems and comprehensively examining the effects of the attacks in single-label, double-label, and triple-label scenarios with different levels of poisoning intensities. Additionally, we investigate the influence of a temporal label-flipping attack, where we study the impact of adversaries available only for specific federated training rounds. Moreover, we propose a novel server-based defense mechanism called SecDefender to detect low-quality models in both IID and non-IID settings of multi-domain environments. Our approach is rigorously evaluated against state-of-the-art alternatives using six benchmark datasets: CIC-Darknet2020, Fashion-MNIST, FEDMNIST, GTSR, HAR, and MNIST. Extensive experiments demonstrate that our proposed SecDefender significantly enhances its performance by over 65% in terms of source class recall, maintaining a low attack success rate. Consequently, there is a 1 to 2% enhancement in global model accuracy compared to existing approaches.

A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling decentralized model training across multiple devices while preserving data privacy. However, the decentralized nature of FL introduces significant security challenges, making it vulnerable to various attacks targeting models, data, and privacy. This survey provides a comprehensive overview of the defense strategies against these attacks, categorizing them into data and model defenses and privacy attacks. We explore pre-aggregation, in-aggregation, and post-aggregation defenses, highlighting their methodologies and effectiveness. Additionally, the survey delves into advanced techniques such as homomorphic encryption and differential privacy to safeguard sensitive information. The integration of blockchain technology for enhancing security in FL environments is also discussed, along with incentive mechanisms to promote active participation among clients. Through this detailed examination, the survey aims to inform and guide future research in developing robust defense frameworks for FL systems.

On the atout ticket learning problem for neural networks and its application in securing federated learning exchanges

Artificial Neural Networks (ANNs) have become the backbone of many real-world applications, including distributed applications relying on Federated Learning (FL). However, several vulnerabilities/attacks have emerged in recent years, affecting the benefits of using ANNs in FL, such as reconstruction attacks and membership inference attacks. These attacks can have severe impacts on both the societal and professional levels. For instance, inferring the presence of a patient’s private health record in a medical study or a clinic database violates the patient’s privacy and can have legal or ethical consequences. Therefore, protecting the data and model from malicious attacks in FL systems is important. This paper introduces the Atout Ticket Learning (ATL) problem. This new problem consists of identifying sensitive parameters (atout tickets) of a neural network model, which, if modified, will increase the model’s loss by at least a given threshold ϵ. First, we formulate ATL as an ℓ0-norm minimization problem, and we derive a lower bound on the number of atout tickets needed to achieve a model degradation of ϵ. Second, we design the Atout Ticket Protocol (ATP) as an effective solution for privacy-preserving in FL systems using atout tickets, along with the benefit of noise perturbations and secure aggregation techniques. Finally, we experiment ATP against FL reconstruction attacks using new selection strategies, namely Inverting Gradients, Deep Leakage, and Improved Deep Leakage. The results show that ATP is highly robust against these attacks.

Federated Learning Frameworks for Secure and Decentralized Authentication

Federated Learning (FL) is a cutting-edge machine learning approach that enables multiple or edge devices to train models collaboratively without sharing sensitive data. This approach not only ensures the privacy and security of data by keeping it localized but also promotes the collective improvement of machine learning models across various participants. A systematic literature review explored integrating Blockchain technology with federated learning. Blockchain's potential to address existing security and privacy vulnerabilities in traditional federated learning systems is analyzed in depth. One of the key benefits of combining Blockchain with FL is enhanced protection against potential attacks, such as data tampering or unauthorized access. The study also examines how Blockchain-based federated learning systems can offer better records and rewards management, contributing to fairer and more transparent systems. In addition, Blockchain's role in improving verification and accountability within federated learning frameworks has been critically evaluated. By integrating Blockchain, federated learning can achieve higher levels of trust and security in collaborative machine-learning processes. The latest research highlights innovative Blockchain-based methods that tackle these challenges, ensuring robust privacy and security measures. Overall, this approach represents a significant advancement in distributed machine learning, aligning with contemporary needs for data protection and collaborative efficiency.

Gradient Scale Monitoring for Federated Learning Systems

As the computational and communicational capabilities of edge and IoT devices grow, so do the opportunities for novel Machine Learning solutions. This leads to an increase in popularity of Federated Learning (FL), especially in cross-device settings. However, while there is a multitude of ongoing research works analyzing various aspects of the FL process, most of them do not focus on issues of operationalization and monitoring. For instance, there is a noticeable lack of research in the topic of effective problem diagnosis in FL systems. This work begins with a case study, in which we have intended to compare the performance of four selected approaches to the topology of FL systems. For this purpose, we have constructed and executed simulations of their training process in a controlled environment. We have analyzed the obtained results and encountered concerning periodic drops in the accuracy for some of the scenarios. We have performed a successful reexamination of the experiments, which led us to diagnose the problem as caused by exploding gradients. In view of those findings, we have formulated a potential new method for the continuous monitoring of the FL training process. The method would hinge on regular local computation of a handpicked metric - the gradient scale coefficient (GSC). We then extend our prior research to include a preliminary analysis of the effectiveness of GSC and average gradients per layer as potentially suitable for FL diagnostics metrics. In order to perform a more thorough examination of their usefulness in different FL scenarios, we simulate the occurrence of the exploding gradient problem, vanishing gradient problem and stable gradient serving as a baseline. We then evaluate the resulting visualizations based on their clarity and computational requirements. We introduce a gradient monitoring suite for the FL training process based on our results.

Evaluating Federated Learning Simulators: A Comparative Analysis of Horizontal and Vertical Approaches.

Federated learning (FL) is a decentralized machine learning approach whereby each device is allowed to train local models, eliminating the requirement for centralized data collecting and ensuring data privacy. Unlike typical typical centralized machine learning, collaborative model training in FL involves aggregating updates from various devices without sending raw data. This ensures data privacy and security while collecting a collective learning from distributed data sources. These devices in FL models exhibit high efficacy in terms of privacy protection, scalability, and robustness, which is contingent upon the success of communication and collaboration. This paper explore the various topologies of both decentralized or centralized in the context of FL. In this respect, we investigated and explored in detail the evaluation of four widly used end-to-end FL frameworks: FedML, Flower, Flute, and PySyft. We specifically focused on vertical and horizontal FL systems using a logistic regression model that aggregated by the FedAvg algorithm. specifically, we conducted experiments on two images datasets, MNIST and Fashion-MNIST, to evaluate their efficiency and performance. Our paper provides initial findings on how to effectively combine horizontal and vertical solutions to address common difficulties, such as managing model synchronization and communication overhead. Our research indicates the trade-offs that exist in the performance of several simulation frameworks for federated learning.

BR-FEEL: A backdoor resilient approach for federated edge learning with fragment-sharing

In the resource-constrained federated edge learning (FEEL) systems, fragment-sharing is an efficient approach for multiple clients to cooperatively train a giant model with billions of parameters. Compared with the classical federated learning schemes where the local model is fully trained and exchanged by each client, the fragment-sharing only requires each client to optionally choose a parameter-fragment to train and share, according to its storage, computing, and networking abilities. However, when the full model is no longer delivered in fragment-sharing, the backdoor attacks hidden behind the fragments become harder to be detected, which introduces formidable challenge for the security of FEEL systems. In this paper, we firstly show that the existing fragment-sharing works suffer a lot from the backdoor attacks. Then, a Backdoor-Resilient approach, named BR-FEEL, is introduced to defend against the potential backdoor attacks. Specifically, a twin model is built by each benign client to integrate the parameter-fragments from others. A knowledge distillation process is designed on each client to transfer the clean knowledge from its twin model to local model. With the twin model and knowledge distillation process, our BR-FEEL approach makes sure that the local models of the benign clients will not be backdoored. Experiments on CIFAR-10 and GTSRB datasets with MobileNetV2 and ResNet-34 are conducted. The numerical results demonstrate the efficacy of BR-FEEL on reducing attack success rates by over 90% compared to other baselines under various attack methods.

Differentially Private Client Selection and Resource Allocation in Federated Learning for Medical Applications Using Graph Neural Networks.

Federated learning (FL) has emerged as a pivotal paradigm for training machine learning models across decentralized devices while maintaining data privacy. In the healthcare domain, FL enables collaborative training among diverse medical devices and institutions, enhancing model robustness and generalizability without compromising patient privacy. In this paper, we propose DPS-GAT, a novel approach integrating graph attention networks (GATs) with differentially private client selection and resource allocation strategies in FL. Our methodology addresses the challenges of data heterogeneity and limited communication resources inherent in medical applications. By employing graph neural networks (GNNs), we effectively capture the relational structures among clients, optimizing the selection process and ensuring efficient resource distribution. Differential privacy mechanisms are incorporated, to safeguard sensitive information throughout the training process. Our extensive experiments, based on the Regensburg pediatric appendicitis open dataset, demonstrated the superiority of our approach, in terms of model accuracy, privacy preservation, and resource efficiency, compared to traditional FL methods. The ability of DPS-GAT to maintain a high and stable number of client selections across various rounds and differential privacy budgets has significant practical implications, indicating that FL systems can achieve strong privacy guarantees without compromising client engagement and model performance. This balance is essential for real-world applications where both privacy and performance are paramount. This study suggests a promising direction for more secure and efficient FL medical applications, which could improve patient care through enhanced predictive models and collaborative data utilization.

TPE-BFL: Training Parameter Encryption scheme for Blockchain based Federated Learning system

Blockchain technology plays a pivotal role in addressing the single point of failure issues in federated learning systems, due to the immutable nature and decentralized architecture. However, traditional blockchain-based federated learning systems still face privacy and security challenges when transmitting training model parameters to individual nodes. Malicious nodes within the system can exploit this process to steal parameters and extract sensitive information, leading to data leakage. To address this problem, we propose a Training Parameter Encryption scheme for Blockchain based Federated Learning system (TPE-BFL). In TPE-BFL, the training parameters of the system model are encrypted using the paillier algorithm with the property of addition homomorphism. This encryption mechanism is integrated into the workflows of three distinct roles within the system: workers, validators, and miners. (1) Workers utilize the paillier encryption algorithm to encrypt training parameters for local training models. (2) Validators decrypt received encrypted training parameters using private keys to verify their validity. (3) Miners receive cryptographic training parameters from validators, validate them, and generate blocks for subsequent global model updates. By implementing the TPE-BFL mechanism, we not only preserve the immutability and decentralization advantages of blockchain technology but also significantly enhance the privacy protection capabilities during data transmission in federated learning systems. In order to verify the security of TPE-BFL, we leverage the semantic security inherent in the Paillier encryption algorithm to theoretically substantiate the security of our system. In addition, we conducted a large number of experiments on real-world data to prove the validity of our proposed TPE-BFL, and when 15% of malicious devices are present, TPE-BFL achieve 92% model accuracy, a 5% improvement over the blockchain-based decentralized FL framework (VBFL).

Implementing and evaluating simple resampling techniques in federated learning for imbalanced data

Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative machine learning. However, the challenge of data imbalance, exacerbated by the non-IID nature of distributed datasets, significantly impacts model performance and fairness in FL systems. This paper investigates the implementation and evaluation of simple resampling techniques to address data imbalance within the FL framework. Using the MIMIC-III healthcare dataset, a simulated FL environment with ten virtual clients was created to test various resampling methods: SMOTE, random undersampling, and a hybrid approach. The study employed logistic regression models and evaluated performance using common and novel FL-specific metrics. Experimental results demonstrate that the hybrid resampling technique significantly outperforms other methods, improving the F1-score by 13.1% and reducing communication rounds by 25.3%. Statistical analyses, including repeated measures ANOVA and hierarchical linear modeling, confirm the robustness of these findings across varied client data distributions. This research provides a replicable framework for addressing data imbalance in FL, contributing to enhanced model fairness and efficiency in privacy-sensitive applications.

On Vehicular Data Aggregation in Federated Learning

Vehicular federated learning systems will be beneficial to predicting traffic events in future intelligent cities. However, they might leak private information upon model updates. Hence, an honest but curious server could infer private information, such as the route of a vehicle. In this study, we elaborate on the nature of such privacy leakage caused by gradient sharing. With a simulated scenario, we focus on determining who is in danger of privacy threats and how successful a route inference attack can be. Results indicate that vanilla federated learning exposes intra-city and commuter traffic to successful location inference attacks. We also found that an adversarial aggregator server successfully infers the moving time of vehicles traveling during low-traffic periods.

FedSHE: privacy preserving and efficient federated learning with adaptive segmented CKKS homomorphic encryption

Unprotected gradient exchange in federated learning (FL) systems may lead to gradient leakage-related attacks. CKKS is a promising approximate homomorphic encryption scheme to protect gradients, owing to its unique capability of performing operations directly on ciphertexts. However, configuring CKKS security parameters involves a trade-off between correctness, efficiency, and security. An evaluation gap exists regarding how these parameters impact computational performance. Additionally, the maximum vector length that CKKS can once encrypt, recommended by Homomorphic Encryption Standardization, is 16384, hampers its widespread adoption in FL when encrypting layers with numerous neurons. To protect gradients’ privacy in FL systems while maintaining practical performance, we comprehensively analyze the influence of security parameters such as polynomial modulus degree and coefficient modulus on homomorphic operations. Derived from our evaluation findings, we provide a method for selecting the optimal multiplication depth while meeting operational requirements. Then, we introduce an adaptive segmented encryption method tailored for CKKS, circumventing its encryption length constraint and enhancing its processing ability to encrypt neural network models. Finally, we present FedSHE, a privacy-preserving and efficient Federated learning scheme with adaptive Segmented CKKS Homomorphic Encryption. FedSHE is implemented on top of the federated averaging (FedAvg) algorithm and is available at https://github.com/yooopan/FedSHE. Our evaluation results affirm the correctness and effectiveness of our proposed method, demonstrating that FedSHE outperforms existing homomorphic encryption-based federated learning research efforts in terms of model accuracy, computational efficiency, communication cost, and security level.

Eco-FL: Enhancing Federated Learning sustainability in edge computing through energy-efficient client selection

In the realm of edge cloud computing (ECC), Federated Learning (FL) revolutionizes the decentralization of machine learning (ML) models by enabling their training across multiple devices. In this way, FL preserves privacy and minimizes the need for centralized data by processing data near the source. From a communication standpoint, only the model weights are exchanged between devices. By avoiding the need to send data to a centralized location for processing, FL reduces the energy required for data transfer and supports more efficient use of computing resources at the edge. FL is particularly advantageous for resource-constrained devices, such as smartphones and IoT devices. However, this limited computational power and battery capacity and the challenge of energy consumption are critical aspects of FL systems. This paper introduces Eco-FL, an innovative methodology designed to optimize energy consumption in FL systems, in the field of Green Edge Cloud Computing (GECC). Our approach employs a device selection process that considers the entropy of the data held by the devices and their available energy reserves. This ensures that devices with lower energy availability are less likely to participate in the training rounds, prioritizing those with higher energy capacities. To evaluate the efficacy of our methodology, we utilize FedEntropy, an entropy-based aggregation method, alongside established aggregation methods such as FedAvg and FedProx for performance comparison. The effectiveness of Eco-FL in reducing energy consumption without compromising the accuracy of the FL process is demonstrated through analyses conducted on three distinct datasets. These analyses vary the β parameter of the Dirichlet distribution and account for scenarios with both homogeneous and heterogeneous initial device charges. Our findings validate Eco-FL’s potential to enhance the sustainability of FL systems by judiciously managing client participation based on energy criteria, presenting a significant step forward in the development of energy-efficient FL.

Privacy and Robustness in Federated Learning: Attacks and Defenses.

As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continues to thrive in this new reality. Existing FL protocol designs have been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this article, we conduct a comprehensive survey on privacy and robustness in FL over the past five years. Through a concise introduction to the concept of FL and a unique taxonomy covering: 1) threat models; 2) privacy attacks and defenses; and 3) poisoning attacks and defenses, we provide an accessible review of this important topic. We highlight the intuitions, key techniques, and fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions toward robust and privacy-preserving FL, and their interplays with the multidisciplinary goals of FL.

BapFL: You can Backdoor Personalized Federated Learning

In federated learning (FL), malicious clients could manipulate the predictions of the trained model through backdoor attacks, posing a significant threat to the security of FL systems. Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. [ 24 ] marks the initial exploration of backdoor attacks within the personalized federated learning (pFL) scenario, where each client constructs a personalized model based on its local data. Notably, the study demonstrates that pFL methods with parameter decoupling can significantly enhance robustness against backdoor attacks. However, in this article, we whistleblow that pFL methods with parameter decoupling are still vulnerable to backdoor attacks. The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts. We analyze two direct causes of the heterogeneous classifiers: (1) data heterogeneity inherently exists among clients and (2) poisoning by malicious clients further exacerbates the data heterogeneity. To address these issues, we propose a two-pronged attack method, BapFL, which comprises two simple yet effective strategies: (1) poisoning only the feature encoder while keeping the classifier fixed and (2) diversifying the classifier through noise introduction to simulate that of the benign clients. Extensive experiments on three benchmark datasets under varying conditions demonstrate the effectiveness of our proposed attack. Additionally, we evaluate the effectiveness of six widely used defense methods and find that BapFL still poses a significant threat even in the presence of the best defense, Multi-Krum. We hope to inspire further research on attack and defense strategies in pFL scenarios. The code is available at: https://github.com/BapFL/code

Scalability and Robustness of Federated Learning Systems: Challenges and Solutions

Federated Learning (FL) revolutionizes traditional machine learning paradigms by enabling collaborative model training across decentralized devices while preserving data privacy. However, its scalability and robustness remain formidable challenges. This paper delves into the complexities of scaling FL systems and enhancing their resilience in dynamic environments. We analyze scalability hurdles stemming from communication overhead, resource constraints, and diverse client populations. Additionally, we scrutinize robustness challenges posed by non-IID data distributions, heterogeneity, and adversarial threats. Proposing novel solutions, including communication-efficient aggregation techniques, adaptive client sampling strategies, and robust aggregation mechanisms, we aim to advance the scalability and robustness of FL systems. Empirical evaluations and case studies underscore the efficacy of these solutions across various applications. Our work outlines future research directions, emphasizing standardization efforts and ethical considerations, to propel the adoption of FL in real-world scenarios.. Keywords: Keywords: Federated Learning, Scalability, Robustness, Privacy Preservation, Communication Efficiency, Heterogeneity, Adversarial Attacks, Differential Privacy.

FedIMP: Parameter Importance-based Model Poisoning attack against Federated learning system

In federated learning systems, the participants collaboratively train a joint model without sharing their raw data. However, these systems are susceptible to poisoning attacks, due to the difficulty in supervising local training processes. Most existing model poisoning attacks target all parameters, resulting in significant model modifications that can be easily detected by checking statistical similarity. We therefore propose FedIMP, an innovative untargeted model poisoning attack method that introduces the concept of parameter importance to enhance stealthiness and effectiveness. We first assess the parameter importance using the Fisher information to selectively poison only those with high importance. Furthermore, we formulate an optimization problem to derive the optimal malicious boosting coefficient such that the attack can evade defense mechanisms while enhancing attack's impact. The experimental results validate the effectiveness of FedIMP, demonstrating its ability to deteriorate model performance and slow down convergence across various aggregation algorithms. Our approach highlights the critical vulnerability in federated learning systems and provides insights for developing more robust defense strategies against poisoning attacks.

Advancements in Federated Learning: Models, Methods, and Privacy

Federated learning (FL) is a promising technique for resolving the rising privacy and security concerns. Its main ingredient is to cooperatively learn the model among the distributed clients without uploading any sensitive data. In this paper, we conducted a thorough review of the related works, following the development context and deeply mining the key technologies behind FL from the perspectives of theory and application. Specifically, we first classify the existing works in FL architecture based on the network topology of FL systems with detailed analysis and summarization. Next, we abstract the current application problems, summarize the general techniques and frame the application problems into the general paradigm of FL base models. Moreover, we provide our proposed solutions for model training via FL. We have summarized and analyzed the existing FedOpt algorithms, and deeply revealed the algorithmic development principles of many first-order algorithms in depth, proposing a more generalized algorithm design framework. With the instantiation of these frameworks, FedOpt algorithms can be simply developed. As privacy and security is the fundamental requirement in FL, we provide the existing attack scenarios and the defense methods. To the best of our knowledge, we are among the first tier to review the theoretical methodology and propose our strategies since there are very few works surveying the theoretical approaches. Our survey targets motivating the development of high-performance, privacy-preserving, and secure methods to integrate FL into real-world applications.

Advancing Federated Learning by Addressing Data and System Heterogeneity

In the emerging field of federated learning (FL), the challenge of heterogeneity, both in data and systems, presents significant obstacles to efficient and effective model training. This talk focuses on the latest advancements and solutions addressing these challenges. The first part of the talk delves into data heterogeneity, a core issue in FL, where data distributions across different clients vary widely and affect FL convergence. We will introduce the FedCor framework addressing this by modeling loss correlations between clients using Gaussian Process and reducing expected global loss. External covariate shift in FL is uncovered, demonstrating that normalization layers are crucial, and layer normalization proves effective. Additionally, class imbalance in FL degrades performance, but our proposed Federated Class-balanced Sampling (Fed-CBS) mechanism reduces this imbalance by employing homomorphic encryption for privacy preservation. The second part of the talk shifts focus to system heterogeneity, an equally critical challenge in FL. System heterogeneity involves the varying computational capabilities, network speeds, and other resource-related constraints of participating devices in FL. To address this, we introduce FedSEA, which is a semi-asynchronous FL framework that addresses accuracy drops by balancing aggregation frequency and predicting local update arrival. Additionally, we discuss FedRepre, a framework specifically designed to enhance FL in real-world environments by addressing challenges including unbalanced local dataset distributions, uneven computational capabilities, and fluctuating network speeds. By introducing a client selection mechanism and a specialized server architecture, FedRepre notably improves the efficiency, scalability, and performance of FL systems. Our talk aims to provide a comprehensive overview of the current research and advancements in tackling both data and system heterogeneity in federated learning. We hope to highlight the path forward for FL, underlining its potential in diverse real-world applications while maintaining data privacy and optimizing resource usage.