Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
Not on the map. Why?
Abstract (arXiv)
We propose Fed-DPRoC, a novel federated learning framework designed to jointly provide differential privacy (DP), Byzantine robustness, and communication efficiency. Central to our approach is the concept of robust-compatible compression, which allows reducing the bi-directional communication overhead without undermining the robustness of the aggregation. We instantiate our framework as RobAJoL, which integrates the Johnson-Lindenstrauss (JL)-based compression mechanism with robust averaging for robustness. Our theoretical analysis establishes the compatibility of JL transform with robust averaging, ensuring that RobAJoL maintains robustness guarantees, satisfies DP, and substantially reduces communication overhead. We further present simulation results on CIFAR-10, Fashion MNIST, and FEMNIST, validating our theoretical claims. We compare RobAJoL with a state-of-the-art communication-efficient and robust FL scheme augmented with DP for a fair comparison, demonstrating that RobAJoL outperforms existing methods in terms of robustness and utility under different Byzantine attacks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 74 references that are in the map. First posted on arXiv 18 Aug 2025.
Builds on
47 of 74 references.
References · 47
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2019Deep Leakage from Gradientscited by 1,021
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
- 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 571
- 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
- 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
35 more
- 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 329
- 2019Error Feedback Fixes SignSGD and other Gradient Compression Schemescited by 310
- 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
- 2017TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learningcited by 256
- 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 236
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
- 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 179
- 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 158
- 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
- 2020Byzantine-Resilient Secure Federated Learningcited by 93
- 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 65
- 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
- 2020Byzantine-Resilient Non-Convex Stochastic Gradient Descentcited by 57
- 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
- 2020FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selectioncited by 36
- 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
- 2021Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?cited by 18
- 2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
- 2019Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketchescited by 17
- 2020Byzantine-Resilient SGD in High Dimensions on Heterogeneous Datacited by 17
- 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
- 2024Federated Learning in Practice: Reflections and Projectionscited by 15
- 2022Bridging Differential Privacy and Byzantine-Robustness via Model Aggregationcited by 13
- 2023Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Ratescited by 12
- 2023Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacycited by 8
- 2024Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromisescited by 7
- 2024Secure Aggregation is Not Private Against Membership Inference Attackscited by 6
- 2023Compressed Private Aggregation for Scalable and Robust Federated Learning over Massive Networkscited by 5
- 2022Distributed Non-Convex Optimization with One-Bit Compressors on Heterogeneous Data: Efficient and Resilient Algorithmscited by 4
- 2023ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitmentcited by 4
- 2025Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learningcited by 4
- 2024LoByITFL: Low Communication Secure and Private Federated Learningcited by 3
- 2024PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learningcited by 3
- 2024TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Datacited by 2
- 2025BICompFL: Stochastic Federated Learning with Bi-Directional Compressioncited by 2
Built on by
Not cited yet.