Computer Science · Literature

Research papers on Federated learning and privacy

Recent and highly-cited academic work on federated learning and privacy, gathered from Semantic Scholar, CrossRef and OpenAlex.

1. Advances and Open Problems in Federated Learning

   Peter Kairouz, H. Brendan McMahan, Brendan Avent, et al. · 2020 · Foundations and Trends® in Machine Learning · 5,391 citations

   Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this monograph discusses recent advances and presents an extensive collection of open problems and challenges.

   Save this paper

2. Federated Learning: Challenges, Methods, and Future Directions

   Tian Li, Anit Kumar Sahu, Ameet Talwalkar, et al. · 2020 · IEEE Signal Processing Magazine · 4,997 citations

   Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.

   Save this paper

3. Federated Learning With Differential Privacy: Algorithms and Performance Analysis

   Kang Wei, Jun Li, Ming Ding, et al. · 2020 · IEEE Transactions on Information Forensics and Security · 2,358 citations

   Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries. Nevertheless, private information can still be divulged by analyzing uploaded parameters from clients, e.g., weights trained in deep neural networks. In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noise is added to parameters at the clients’ side before aggregating, namely, noising before model aggregation FL (NbAFL). First, we prove that the NbAFL can satisfy DP under distinct protection levels by properly adapting diff

   Save this paper

4. Secure, privacy-preserving and federated machine learning in medical imaging

   Georgios Kaissis, Marcus R. Makowski, Daniel Rückert, et al. · 2020 · Nature Machine Intelligence · 1,457 citations

   The broad application of artificial intelligence techniques in medicine is currently hindered by limited dataset availability for algorithm training and validation, due to the absence of standardized electronic medical records, and strict legal and ethical requirements to protect patient privacy. In medical imaging, harmonized data exchange formats such as Digital Imaging and Communication in Medicine and electronic data storage are the standard, partially addressing the first issue, but the requirements for privacy preservation are equally strict. To prevent patient privacy compromise while promoting scientific research on large datasets that aims to improve patient care, the implementation

   Save this paper

5. Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT

   Yunlong Lu, Xiaohong Huang, Yueyue Dai, et al. · 2019 · IEEE Transactions on Industrial Informatics · 1,255 citations

   The rapid increase in the volume of data generated from connected devices in industrial Internet of Things paradigm, opens up new possibilities for enhancing the quality of service for the emerging applications through data sharing. However, security and privacy concerns (e.g., data leakage) are major obstacles for data providers to share their data in wireless networks. The leakage of private data can lead to serious issues beyond financial loss for the providers. In this article, we first design a blockchain empowered secure data sharing architecture for distributed multiple parties. Then, we formulate the data sharing problem into a machine-learning problem by incorporating privacy-preser

   Save this paper

6. A Hybrid Approach to Privacy-Preserving Federated Learning

   Stacey Truex, Nathalie Baracaldo, Ali Anwar, et al. · 2019 · 953 citations

   Federated learning facilitates the collaborative training of models without the sharing of raw data. However, recent attacks demonstrate that simply maintaining data locality during training processes does not provide sufficient privacy guarantees. Rather, we need a federated learning system capable of preventing inference over both the messages exchanged during training and the final trained model while ensuring the resulting model also has acceptable predictive accuracy. Existing federated learning approaches either use secure multiparty computation (SMC) which is vulnerable to inference or differential privacy which can lead to low accuracy given a large number of parties with relatively

   Save this paper

7. Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach

   Yi Liu, James J. Q. Yu, Jiawen Kang, et al. · 2020 · IEEE Internet of Things Journal · 704 citations

   Existing traffic flow forecasting approaches by deep learning models achieve excellent success based on a large volume of data sets gathered by governments and organizations. However, these data sets may contain lots of user's private data, which is challenging the current prediction approaches as user privacy is calling for the public concern in recent years. Therefore, how to develop accurate traffic prediction while preserving privacy is a significant problem to be solved, and there is a tradeoff between these two objectives. To address this challenge, we introduce a privacy-preserving machine learning technique named federated learning (FL) and propose an FL-based gated recurrent unit ne

   Save this paper

8. A Comprehensive Survey of Privacy-preserving Federated Learning

   Xuefei Yin, Yanming Zhu, Jiankun Hu · 2021 · ACM Computing Surveys · 621 citations

   The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the distributed intermediate results. The emerging privacy-preserving FL (PPFL) has been heralded as a solution to generic privacy-preserving machine learning. However, the challenge of protecting data privacy while maintaining the data utility through machine learning still remains. In this article, we present a comprehensive and systematic survey on the PPFL based on our proposed 5W-scenario-based taxonomy. We analyze the privacy leakage risks in the FL from five aspects, summarize existing methods, and identify future research direc

   Save this paper

9. Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

   Yang Zhao, Jun Zhao, Linshan Jiang, et al. · 2020 · IEEE Internet of Things Journal · 596 citations

   Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a smart home system. To help manufacturers develop a smart home system, we design a federated learning (FL) system leveraging a reputation mechanism to assist home appliance manufacturers to train a machine learning model based on customers’ data. Then, manufacturers can predict customers’ requirements and consumption behaviors in the future. The working flow of the system includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile-edge computing (MEC) server. Customers collect data from variou

   Save this paper

10. Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results

    Xiaoxiao Li, Yufeng Gu, Nicha C. Dvornek, et al. · 2020 · Medical Image Analysis · 473 citations

    Deep learning models have shown their advantage in many different tasks, including neuroimage analysis. However, to effectively train a high-quality deep learning model, the aggregation of a significant amount of patient information is required. The time and cost for acquisition and annotation in assembling, for example, large fMRI datasets make it difficult to acquire large numbers at a single site. However, due to the need to protect the privacy of patient data, it is hard to assemble a central database from multiple institutions. Federated learning allows for population-level models to be trained without centralizing entities' data by transmitting the global model to local entities, train

    Save this paper

11. Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning

    Haokun Fang, Quan Qian · 2021 · Future Internet · 421 citations

    Privacy protection has been an important concern with the great success of machine learning. In this paper, it proposes a multi-party privacy preserving machine learning framework, named PFMLP, based on partially homomorphic encryption and federated learning. The core idea is all learning parties just transmitting the encrypted gradients by homomorphic encryption. From experiments, the model trained by PFMLP has almost the same accuracy, and the deviation is less than 1%. Considering the computational overhead of homomorphic encryption, we use an improved Paillier algorithm which can speed up the training by 25–28%. Moreover, comparisons on encryption key length, the learning network structu

    Save this paper

12. Privacy‐preserving federated learning based on multi‐key homomorphic encryption

    Jing Ma, Si‐Ahmed Naas, Stephan Sigg, et al. · 2022 · International Journal of Intelligent Systems · 413 citations

    With the advance of machine learning and the Internet of Things (IoT), security and privacy have become critical concerns in mobile services and networks. Transferring data to a central unit violates the privacy of sensitive data. Federated learning mitigates this need to transfer local data by sharing model updates only. However, privacy leakage remains an issue. This paper proposes xMK-CKKS, an improved version of the MK-CKKS multi-key homomorphic encryption protocol, to design a novel privacy-preserving federated learning scheme. In this scheme, model updates are encrypted via an aggregated public key before sharing with a server for aggregation. For decryption, a collaboration among all

    Save this paper

13. Federated Learning for Privacy-Preserving AI

    RN Shashi Vardhan · 2025 · International Journal of Research Publication and Reviews · 3 citations

    The rapid adoption of Artificial Intelligence (AI) across industries, particularly in healthcare, finance, and smart devices, has introduced significant concerns regarding data privacy, security, and compliance with regulations such as GDPR, HIPAA, and CCPA. Traditional centralized machine learning (ML) models require large-scale data aggregation, increasing risks of data breaches, misuse, and unauthorized access. Federated Learning (FL) has emerged as a transformative solution, allowing multiple edge devices or organizations to collaboratively train machine learning models without sharing raw data. This paper explores the principles, advantages, and challenges of FL and conducts an

    Save this paper

14. Federated Learning for Privacy-Preserving Employee Performance Analytics

    Jay Barach · 2025 · IEEE Access · 3 citations

    Save this paper

15. Federated Learning: Privacy-Preserving Machine Learning in Cloud Environments

    Bangar Raju Cherukuri · 2024 · International Journal of Science and Research (IJSR) · 1 citations

    Save this paper

16. Federated Learning Architectures for Privacy Preserving Financial Fraud Detection Systems

    Favour . C. Ezeugboaja · 2025 · Frontiers in Emerging Artificial Intelligence and Machine Learning · 1 citations

    The increasing complexity and intensity of cases of financial fraud, such as synthetic identity fraud and international money laundering, have become significant concerns for classic fraud detection solutions, especially under strict data privacy regulations such as GDPR or EU Artificial Intelligence Act guidelines. This study focuses on the very pressing need to pursue high fraud detection performance while simultaneously ensuring user data confidentiality for highly fragmented financial systems. The study uses federated learning (FL) designs to analyse interesting opportunities for possibly entirely decentralized machine learning functions among diverse financial agencies without any need

    Save this paper

17. Privacy Preserving Federated Learning Efficiency Optimization Algorithm based on Differential Privacy

    Rui Xie · 2025 · Computer Fraud and Security · 1 citations

    With the advancement of information technology, data security and user privacy protection have become paramount. To achieve efficient privacy protection in a federated learning environment, a differential privacy algorithm is designed using the eXtreme Gradient Boosting (XGBoost) algorithm. This algorithm optimizes the privacy protection process by applying differential privacy to the optimal segmentation point in a weak classifier. Additionally, to address the multi-party collaboration challenge in federated learning, a differential privacy construction scheme based on multi-party collaboration is proposed. The results indicate that the running times of differential privacy algorithms based

    Save this paper

18. Federated Learning for Privacy-Preserving Big Data Analytics in Distributed Systems

    Ahmed Gheni Dawood, Ekhlas Muthanna Turki · 2026 · JOINCS (Journal of Informatics, Network, and Computer Science)

    Federated Learning (FL) is an important concept in big data analytics because it has changed the way collaborative model training can be done on devices that are decentralized while ensuring user privacy, an essential requirement in an accurate evidence-based and regulated environment with even stricter requirements from regulations like GDPR, HIPAA, CCPA and future laws on data sovereignty. This paper analyzed FL in depth. It described foundational concepts, architectural approaches, algorithmic approaches, real-world and practical applications and challenges in distributed systems. Key issues such as communication overhead, data heterogeneity, security risks, fairness, scalability, energy

    Save this paper

19. Fedssl: privacy-preserving federated self-supervised learning with differential privacy guarantees for heterogeneous edge environments

    Zayyanu Yunusa · 2025 · Journal of Artificial Intelligence Machine Learning and Neural Network

    In this study, we delve into the significant impact of AI, investigating its multifaceted consequences on society. In a rapidly evolving digital landscape, the integration of artificial intelligence has emerged as a transformative force in reshaping human progress and well-being. Drawing from historical perspectives, we trace the evolution of AI and its transformative journey. Our research aims to comprehensively analyze approaches for fostering responsible AI growth while mitigating potential hazards. By illuminating both the promise and perils of AI, this study contributes to informed decision-making in the unfolding AL era. This research explores the innovative utilization of AI technolog

    Save this paper

20. Privacy-preserving federated learning with differential privacy for healthcare AI: a convergence and utility analysis

    Aruna Pavate · 2025 · Journal of Artificial Intelligence Machine Learning and Neural Network

    Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without sharing raw patient data, offering a paradigm shift for privacy-sensitive medical AI. However, FL remains vulnerable to gradient inversion attacks and model poisoning, necessitating formal privacy guarantees. This paper presents a comprehensive analysis of Differential Privacy (DP)-augmented Federated Learning for healthcare AI applications, specifically Electronic Health Record (EHR) classification. We evaluate three aggregation strategies FedAvg, FedProx, and the proposed FedNova-DP across simulated environments with 10, 25, and 50 heterogeneous clients under both IID and non-IID

    Save this paper

21. Federated Learning for Privacy-Preserving Artificial Intelligence in Healthcare Systems

    Ashwini Vikas Ghogare · 2025 · Anusandhanvallari

    This paper explores how Federated Learning (FL) systems can be strengthened through the integration of Differential Privacy (DP). While FL allows multiple clients to collaboratively train a shared model without exposing raw data, model updates exchanged during training may still leak sensitive information. To address this, DP is applied using gradient clipping and Gaussian noise addition, thereby reducing the risk of privacy breaches. The study employs the Fed Avg algorithm in simulation experiments with ten clients under three noise levels (σ = 0.0, 0.5, 1.0), evaluating outcomes in terms of accuracy, log loss, and an illustrative Rényi-DP privacy budget (ε). Results highlight the trade-off

    Save this paper