Differentially Private Federated Learning: A Client Level Perspective
Not on the map. Why?
Abstract (arXiv)
Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to share the data. However, the protocol is vulnerable to differential attacks, which could originate from any party contributing during federated optimization. In such an attack, a client's contribution during training and information about their data set is revealed through analyzing the distributed model. We tackle this problem and propose an algorithm for client sided differential privacy preserving federated optimization. The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance. Empirical studies suggest that given a sufficiently large number of participating clients, our proposed procedure can maintain client-level differential privacy at only a minor cost in model performance.
Key facts. Cited by 451 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 102; 2022: 84; 2023: 81; 2024: 85; 2025: 54; 2026: 45.
451 papers.
Sort:
By area:
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
- 2021Federated Learning on Non-IID Data: A Surveycited by 345
- 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
- 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
- 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 135
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
- 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
- 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
- 2021Label Leakage and Protection in Two-party Split Learningcited by 87
38 more
- 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 86
- 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 85
- 2021Federated Learning: Opportunities and Challengescited by 83
- 2021Federated Reconstruction: Partially Local Federated Learningcited by 78
- 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
- 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
- 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 66
- 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
- 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
- 2023Federated Learning of Gboard Language Models with Differential Privacycited by 64
- 2021Provably Secure Federated Learning against Malicious Clientscited by 60
- 2021Federated Multi-Armed Banditscited by 59
- 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
- 2022Personalized Subgraph Federated Learningcited by 54
- 2021Differentially Private Federated Knowledge Graphs Embeddingcited by 45
- 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
- 2021FLOP: Federated Learning on Medical Datasets using Partial Networkscited by 42
- 2022A Survey on Heterogeneous Federated Learningcited by 42
- 2021Gradient-Leakage Resilient Federated Learningcited by 40
- 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
- 2021AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learningcited by 39
- 2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
- 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
- 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
- 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 38
- 2021On the Convergence and Calibration of Deep Learning with Differential Privacycited by 36
- 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
- 2021GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learningcited by 35
- 2021Game of Gradients: Mitigating Irrelevant Clients in Federated Learningcited by 35
- 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 35
- 2022SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compressioncited by 34
- 2022Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directionscited by 34
- 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 34
- 2022Trading Off Privacy, Utility and Efficiency in Federated Learningcited by 33
- 2023Make Landscape Flatter in Differentially Private Federated Learningcited by 33
- 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
- 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 32
50 most cited of 451 All 451 (JSON)
- 2026Federated Agent Optimization1 Oct 2026
- 2026Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning24 Sep 2026
- 2026FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift17 Sep 2026
- 2026Privacy-Preserving Split Learning for Federated LLM Fine-Tuning9 Sep 2026
- 2026Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems2 Sep 2026
- 2026Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks2 Sep 2026
- 2026Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis1 Sep 2026
- 2026SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring27 Aug 2026
- 2026Mitigating Explanation Leakage in Financial Fraud Detection Systems23 Aug 2026
- 2026Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning6 Aug 2026
- 2026Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation1 Aug 2026
- 2026Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View25 Jul 2026
38 more
- 2026Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries23 Jul 2026
- 2026Robust Federated Learning Under Real-World Client Churn8 Jul 2026
- 2026TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization16 Jun 2026
- 2026Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning15 Jun 2026
- 2026Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages15 Jun 2026
- 2026CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning6 Jun 2026
- 2026DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning13 May 2026
- 2026DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models11 May 2026
- 2026Privacy-Preserving Distributed Learning in IoT Systems: A Unified Threat Model and Evaluation Framework10 May 2026
- 2026UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment8 May 2026
- 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy25 Apr 2026
- 2026Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization24 Apr 2026
- 2026PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talking-Head Generation9 Apr 2026
- 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation8 Apr 2026
- 2026FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs7 Apr 2026
- 2026Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization1 Apr 2026
- 2026TrustFed: Enabling Trustworthy Medical AI under Data Privacy Constraints23 Mar 2026
- 2026Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication22 Mar 2026
- 2026ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery18 Mar 2026
- 2026Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap13 Mar 2026
- 2026An Efficient Unsupervised Federated Learning Approach for Anomaly Detection in Heterogeneous IoT Networks27 Feb 2026
- 2026Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation24 Feb 2026
- 2026DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models23 Feb 2026
- 2026PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems21 Feb 2026
- 2026FedEMA-Distill: Exponential Moving Average Guided Knowledge Distillation for Robust Federated Learning15 Feb 2026
- 2026Floe: Federated Specialization for Real-Time LLM-SLM Inference15 Feb 2026
- 2026TIP: Resisting Gradient Inversion via Targeted Interpretable Perturbation in Federated Learning12 Feb 2026
- 2026ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation9 Feb 2026
- 2026Federated Proximal Optimization for Privacy-Preserving Heart Disease Prediction: A Controlled Simulation Study on Non-IID Clinical Data23 Jan 2026
- 2026FSL-BDP: Federated Survival Learning with Bayesian Differential Privacy for Credit Risk Modeling16 Jan 2026
- 2026One-Shot Federated Ridge Regression: Exact Recovery via Sufficient Statistic Aggregation13 Jan 2026
- 2026Byzantine-Robust Federated Learning Framework with Post-Quantum Secure Aggregation for Real-Time Threat Intelligence Sharing in Critical IoT Infrastructure3 Jan 2026
- 2026FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing2 Jan 2026
- 2025First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions25 Dec 2025
- 2025Evaluating Adversarial Attacks on Federated Learning for Temperature Forecasting15 Dec 2025
- 2025Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain14 Dec 2025
- 2025DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm31 Oct 2025
- 2025Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station27 Oct 2025
50 newest of 451 All 451 (JSON)
- 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
- 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
- 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 86
- 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 25
- 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
- 2024FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learningcited by 10
- 2024Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearningcited by 7
- 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learningcited by 4
- 2024Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilitiescited by 3
- 2024Securing Federated Learning against Backdoor Threats with Foundation Model Integrationcited by 3
- 2024Efficient Federated Unlearning under Plausible Deniabilitycited by 1
- 2024Data Poisoning and Leakage Analysis in Federated Learningcited by 0
12 most cited of 14 All 14 (JSON)
- 2025DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences13 Jul 2025
- 2024Upcycling Noise for Federated Unlearning7 Dec 2024
- 2024Securing Federated Learning against Backdoor Threats with Foundation Model Integration23 Oct 2024
- 2024Efficient Federated Unlearning under Plausible Deniability13 Oct 2024
- 2024Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning1 Oct 2024
- 2024Data Poisoning and Leakage Analysis in Federated Learning19 Sep 2024
- 2024FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning9 Feb 2024
- 2024Security and Privacy Challenges of Large Language Models: A Survey30 Jan 2024
- 2024Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities18 Jan 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
- 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning25 Aug 2022
12 newest of 14 All 14 (JSON)
- 2026Federated Agent Optimizationcited by 0
- 2026Federated Agent Optimization1 Oct 2026
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
- 2021Federated Learning on Non-IID Data: A Surveycited by 345
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
- 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 137
- 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 135
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
- 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
- 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
- 2021Label Leakage and Protection in Two-party Split Learningcited by 87
- 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 85
- 2021Federated Learning: Opportunities and Challengescited by 83
12 most cited of 433 All 433 (JSON)
- 2026Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning24 Sep 2026
- 2026FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift17 Sep 2026
- 2026Privacy-Preserving Split Learning for Federated LLM Fine-Tuning9 Sep 2026
- 2026Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems2 Sep 2026
- 2026Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks2 Sep 2026
- 2026Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis1 Sep 2026
- 2026SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring27 Aug 2026
- 2026Mitigating Explanation Leakage in Financial Fraud Detection Systems23 Aug 2026
- 2026Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning6 Aug 2026
- 2026Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation1 Aug 2026
- 2026Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View25 Jul 2026
- 2026Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries23 Jul 2026
12 newest of 433 All 433 (JSON)