A Hybrid Approach to Privacy-Preserving Federated Learning
Not on the map. Why?
Abstract (arXiv)
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 small amounts of data each. In this paper, we present an alternative approach that utilizes both differential privacy and SMC to balance these trade-offs. Combining differential privacy with secure multiparty computation enables us to reduce the growth of noise injection as the number of parties increases without sacrificing privacy while maintaining a pre-defined rate of trust. Our system is therefore a scalable approach that protects against inference threats and produces models with high accuracy. Additionally, our system can be used to train a variety of machine learning models, which we validate with experimental results on 3 different machine learning algorithms. Our experiments demonstrate that our approach out-performs state of the art solutions.
Key facts. Cited by 210 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Dec 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 51; 2022: 49; 2023: 34; 2024: 42; 2025: 27; 2026: 7.
210 papers.
Sort:
By area:
- 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
- 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
- 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
- 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
- 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
- 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
- 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2021Federated Learning: A Signal Processing Perspectivecited by 49
- 2022A Survey on Heterogeneous Federated Learningcited by 42
38 more
- 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
- 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
- 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
- 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
- 2021Non-IID data and Continual Learning processes in Federated Learning: A long road aheadcited by 36
- 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
- 2021Source Inference Attacks in Federated Learningcited by 34
- 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 33
- 2022Trading Off Privacy, Utility and Efficiency in Federated Learningcited by 33
- 2021Differentially Private Federated Bayesian Optimization with Distributed Explorationcited by 32
- 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
- 2021FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Datacited by 31
- 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 31
- 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
- 2021Federated f-Differential Privacycited by 29
- 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
- 2022A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologiescited by 28
- 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 27
- 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
- 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
- 2021Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errorscited by 25
- 2022Rethinking Portrait Matting with Privacy Preservingcited by 25
- 2024Decentralized Federated Learning: A Survey on Security and Privacycited by 25
- 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
- 2022Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realizationcited by 19
- 2022How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?cited by 19
- 2021Dopamine: Differentially Private Federated Learning on Medical Datacited by 18
- 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
- 2021Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryptioncited by 18
- 2021Gradient Leakage Attack Resilient Deep Learningcited by 18
- 2022Improving Federated Learning Face Recognition via Privacy-Agnostic Clusterscited by 18
- 2021Adversarial training in communication constrained federated learningcited by 17
- 2022FedSysID: A Federated Approach to Sample-Efficient System Identificationcited by 17
- 2023Subspace based Federated Unlearningcited by 17
- 2023FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Modelscited by 17
- 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 17
- 2023Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregationcited by 16
- 2021A Systematic Survey of Blockchained Federated Learningcited by 15
50 most cited of 210 All 210 (JSON)
- 2026Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems2 Sep 2026
- 2026SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring27 Aug 2026
- 2026Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View25 Jul 2026
- 2026TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction5 Jul 2026
- 2026Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation22 Apr 2026
- 2026Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning16 Mar 2026
- 2026SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy14 Jan 2026
- 2025Scalable Cloud-Native Architectures for Intelligent PMU Data Processing23 Dec 2025
- 2025DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication15 Dec 2025
- 2025Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning24 Nov 2025
- 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients24 Oct 2025
- 2025Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approaches29 Sep 2025
38 more
- 2025Emerging Paradigms for Securing Federated Learning Systems25 Sep 2025
- 2025Distribution-Controlled Client Selection to Improve Federated Learning Strategies25 Sep 2025
- 2025FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection12 Sep 2025
- 2025Federated Nonlinear System Identification20 Aug 2025
- 2025FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness13 Aug 2025
- 2025Federated Learning for Commercial Image Sources17 Jul 2025
- 2025Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning25 Jun 2025
- 2025FedGA-Tree: Federated Decision Tree using Genetic Algorithm9 Jun 2025
- 2025Differential Privacy Analysis of Decentralized Gossip Averaging under Varying Threat Models26 May 2025
- 2025LAPA-based Dynamic Privacy Optimization for Wireless Federated Learning in Heterogeneous Environments26 May 2025
- 2025Topology-Aware Knowledge Propagation in Decentralized Learning16 May 2025
- 2025Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning15 May 2025
- 2025CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection2 Apr 2025
- 2025Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI20 Mar 2025
- 2025Privacy-Preserved Automated Scoring using Federated Learning for Educational Research12 Mar 2025
- 2025Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimization1 Mar 2025
- 2025Differentially Private Federated Learning With Time-Adaptive Privacy Spending25 Feb 2025
- 2025Privacy-Preserving Dataset Combination9 Feb 2025
- 2025Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning8 Feb 2025
- 2025Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs7 Feb 2025
- 2025PBM-VFL: Vertical Federated Learning with Feature and Sample Privacy23 Jan 2025
- 2025TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning9 Jan 2025
- 2024Recommender Engine Driven Client Selection in Federated Brain Tumor Segmentation28 Dec 2024
- 2024Efficiently Achieving Secure Model Training and Secure Aggregation to Ensure Bidirectional Privacy-Preservation in Federated Learning16 Dec 2024
- 2024Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression14 Dec 2024
- 2024Evaluating the Potential of Federated Learning for Maize Leaf Disease Prediction10 Dec 2024
- 2024Membership Inference Attacks and Defenses in Federated Learning: A Survey9 Dec 2024
- 2024eFedLLM: Efficient LLM Inference Based on Federated Learning24 Nov 2024
- 2024Artificial Intelligence in Pediatric Echocardiography: Exploring Challenges, Opportunities, and Clinical Applications with Explainable AI and Federated Learning15 Nov 2024
- 2024NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA6 Nov 2024
- 2024Trustworthy Federated Learning: Privacy, Security, and Beyond3 Nov 2024
- 2024A Study of Secure Algorithms for Vertical Federated Learning: Take Secure Logistic Regression as an Example30 Oct 2024
- 2024Byzantine-Robust Aggregation for Securing Decentralized Federated Learning26 Sep 2024
- 2024Immersion and Invariance-based Coding for Privacy-Preserving Federated Learning25 Sep 2024
- 2024Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Review24 Sep 2024
- 2024A Multi-Level Approach for Class Imbalance Problem in Federated Learning for Remote Industry 4.0 Applications24 Sep 2024
- 2024Analyzing Inference Privacy Risks Through Gradients in Machine Learning29 Aug 2024
- 2024On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps27 Jul 2024
50 newest of 210 All 210 (JSON)
- 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 31
- 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 27
- 2023Subspace based Federated Unlearningcited by 17
- 2023Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learningcited by 11
- 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learningcited by 7
- 2023Security and Privacy Issues of Federated Learningcited by 2
- 2025FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairnesscited by 0
- 2025Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approachescited by 0
- 2025Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approaches29 Sep 2025
- 2025FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness13 Aug 2025
- 2024Membership Inference Attacks and Defenses in Federated Learning: A Survey9 Dec 2024
- 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics10 Jan 2024
- 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning28 Nov 2023
- 2023Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learning30 Sep 2023
- 2023Security and Privacy Issues of Federated Learning22 Jul 2023
- 2023Subspace based Federated Unlearning24 Feb 2023
- 2024eFedLLM: Efficient LLM Inference Based on Federated Learning24 Nov 2024
- 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
- 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
- 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
- 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
- 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 69
- 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
- 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2021Federated Learning: A Signal Processing Perspectivecited by 49
- 2022A Survey on Heterogeneous Federated Learningcited by 42
12 most cited of 196 All 196 (JSON)
- 2026Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems2 Sep 2026
- 2026SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring27 Aug 2026
- 2026Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View25 Jul 2026
- 2026Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation22 Apr 2026
- 2026Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning16 Mar 2026
- 2026SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy14 Jan 2026
- 2025Scalable Cloud-Native Architectures for Intelligent PMU Data Processing23 Dec 2025
- 2025DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication15 Dec 2025
- 2025Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning24 Nov 2025
- 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradients24 Oct 2025
- 2025Emerging Paradigms for Securing Federated Learning Systems25 Sep 2025
- 2025Distribution-Controlled Client Selection to Improve Federated Learning Strategies25 Sep 2025
12 newest of 196 All 196 (JSON)