mlsanityData to 7 Oct 2026

Privacy-preserving Collaborative Learning with Automatic Transformation Search

arXiv 2011.12505 ↗First posted 25 Nov 2020cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary can fully recover the sensitive training samples from the shared gradients. Such reconstruction attacks pose severe threats to collaborative learning. Hence, effective mitigation solutions are urgently desired. In this paper, we propose to leverage data augmentation to defeat reconstruction attacks: by preprocessing sensitive images with carefully-selected transformation policies, it becomes infeasible for the adversary to extract any useful information from the corresponding gradients. We design a novel search method to automatically discover qualified policies. We adopt two new metrics to quantify the impacts of transformations on data privacy and model usability, which can significantly accelerate the search speed. Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 8; 2024: 7; 2025: 7; 2026: 2.

31 papers.

Sort:

By area:

  1. 2023Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimizationcited by 65
  2. 2021Bayesian Framework for Gradient Leakagecited by 34
  3. 2021EasyFL: A Low-code Federated Learning Platform For Dummiescited by 20
  4. 2021Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learningcited by 16
  5. 2023Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?cited by 13
  6. 2024Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attackscited by 13
  7. 2022Concealing Sensitive Samples against Gradient Leakage in Federated Learningcited by 11
  8. 2024One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversitycited by 8
  9. 2024Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attackscited by 7
  10. 2025"X of Information'' Continuum: A Survey on AI-Driven Multi-dimensional Metrics for Next-Generation Networked Systemscited by 7
  11. 2022FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systemscited by 6
  12. 2023Understanding Deep Gradient Leakage via Inversion Influence Functionscited by 6
19 more
  1. 2022An Interpretable Federated Learning-based Network Intrusion Detection Frameworkcited by 4
  2. 2023Maximum Knowledge Orthogonality Reconstruction with Gradients in Federated Learningcited by 4
  3. 2023PPIDSG: A Privacy-Preserving Image Distribution Sharing Scheme with GAN in Federated Learningcited by 4
  4. 2023Mutual Information Regularization for Vertical Federated Learningcited by 3
  5. 2024Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memorycited by 3
  6. 2022Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Studycited by 2
  7. 2025SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decompositioncited by 2
  8. 2023Privacy Protectability: An Information-theoretical Approachcited by 1
  9. 2025FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fieldscited by 1
  10. 2023OASIS: Offsetting Active Reconstruction Attacks in Federated Learningcited by 0
  11. 2024Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspectivecited by 0
  12. 2024Privacy-Preserving Federated Learning via Dataset Distillationcited by 0
  13. 2024Anomalous Client Detection in Federated Learningcited by 0
  14. 2025Secure Generalization through Stochastic Bidirectional Parameter Updates Using Dual-Gradient Mechanismcited by 0
  15. 2025DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systemscited by 0
  16. 2025Evaluating Selective Encryption Against Gradient Inversion Attackscited by 0
  17. 2025Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Maskingcited by 0
  18. 2026A Unified Masked Jigsaw Puzzle Framework for Vision and Language Modelscited by 0
  19. 2026ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recoverycited by 0