mlsanityData to 14 Oct 2026

Concealing Sensitive Samples against Gradient Leakage in Federated Learning

arXiv 2209.05724 ↗First posted 13 Sep 2022cs.LG cs.CR cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to model inversion attacks, where adversaries reconstruct users private data via eavesdropping on the shared gradient information. We hypothesize that a key factor in the success of such attacks is the low entanglement among gradients per data within the batch during stochastic optimization. This creates a vulnerability that an adversary can exploit to reconstruct the sensitive data. Building upon this insight, we present a simple, yet effective defense strategy that obfuscates the gradients of the sensitive data with concealed samples. To achieve this, we propose synthesizing concealed samples to mimic the sensitive data at the gradient level while ensuring their visual dissimilarity from the actual sensitive data. Compared to the previous art, our empirical evaluations suggest that the proposed technique provides the strongest protection while simultaneously maintaining the FL performance.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 22 of its 46 references that are in the map. First posted on arXiv 13 Sep 2022.

Builds on

22 of 46 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2019Advances and Open Problems in Federated Learningcited by 3,046
  7. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  8. 2019Deep Leakage from Gradientscited by 1,021
  9. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  10. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  11. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  12. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
10 more
  1. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  2. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  3. 2021Gradient Inversion with Generative Image Priorcited by 101
  4. 2020R-GAP: Recursive Gradient Attack on Privacycited by 97
  5. 2020Provable Defense against Privacy Leakage in Federated Learning from Representation Perspectivecited by 94
  6. 2020InstaHide: Instance-hiding Schemes for Private Distributed Learningcited by 90
  7. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  8. 2021Gradient-Leakage Resilient Federated Learningcited by 40
  9. 2020Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attackscited by 32
  10. 2020Privacy-preserving Collaborative Learning with Automatic Transformation Searchcited by 31

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 4; 2025: 3; 2026: 2.

11 papers.

  1. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  2. 2022FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systemscited by 6
  3. 2023Gradient Leakage Defense with Key-Lock Module for Federated Learningcited by 4
  4. 2024FedDP: Privacy-preserving method based on federated learning for histopathology image segmentationcited by 3
  5. 2025SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decompositioncited by 2
  6. 2024FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defensescited by 1
  7. 2024Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoisingcited by 1
  8. 2024Privacy-Preserving Federated Learning via Dataset Distillationcited by 0
  9. 2025Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Maskingcited by 0
  10. 2026SpooFL: Spoofing Federated Learningcited by 0
  11. 2026UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversioncited by 0