mlsanityData to 14 Oct 2026

Random Gradient Masking as a Defensive Measure to Deep Leakage in Federated Learning

arXiv 2408.08430 ↗First posted 15 Aug 2024cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning(FL), in theory, preserves privacy of individual clients' data while producing quality machine learning models. However, attacks such as Deep Leakage from Gradients(DLG) severely question the practicality of FL. In this paper, we empirically evaluate the efficacy of four defensive methods against DLG: Masking, Clipping, Pruning, and Noising. Masking, while only previously studied as a way to compress information during parameter transfer, shows surprisingly robust defensive utility when compared to the other three established methods. Our experimentation is two-fold. We first evaluate the minimum hyperparameter threshold for each method across MNIST, CIFAR-10, and lfw datasets. Then, we train FL clients with each method and their minimum threshold values to investigate the trade-off between DLG defense and training performance. Results reveal that Masking and Clipping show near to none degradation in performance while obfuscating enough information to effectively defend against DLG.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 15 Aug 2024.

Builds on

20 of 24 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2019Deep Leakage from Gradientscited by 1,021
  6. 2018How To Backdoor Federated Learningcited by 765
  7. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  9. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  10. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  12. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
8 more
  1. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  2. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 118
  3. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  4. 2021GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learningcited by 74
  5. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 68
  6. 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
  7. 2019Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradientscited by 32
  8. 2022BEAS: Blockchain Enabled Asynchronous & Secure Federated Machine Learningcited by 7

Built on by

Not cited yet.