mlsanityData to 7 Oct 2026

Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates

arXiv 2506.11413 ↗First posted 13 Jun 2025cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables decentralized machine learning without sharing raw data, allowing multiple clients to collaboratively learn a global model. However, studies reveal that privacy leakage is possible under commonly adopted FL protocols. In particular, a server with access to client gradients can synthesize data resembling the clients' training data. In this paper, we introduce a novel threat model in FL, named the maliciously curious client, where a client manipulates its own gradients with the goal of inferring private data from peers. This attacker uniquely exploits the strength of a Byzantine adversary, traditionally aimed at undermining model robustness, and repurposes it to facilitate data reconstruction attack. We begin by formally defining this novel client-side threat model and providing a theoretical analysis that demonstrates its ability to achieve significant reconstruction success during FL training. To demonstrate its practical impact, we further develop a reconstruction algorithm that combines gradient inversion with malicious update strategies. Our analysis and experimental results reveal a critical blind spot in FL defenses: both server-side robust aggregation and client-side privacy mechanisms may fail against our proposed attack. Surprisingly, standard server- and client-side defenses designed to enhance robustness or privacy may unintentionally amplify data leakage. Compared to the baseline approach, a mistakenly used defense may instead improve the reconstructed image quality by 10-15%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 50 of its 79 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

50 of 79 references.

References · 50

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2019Deep Leakage from Gradientscited by 1,004
  8. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  9. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  10. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  11. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  12. 2018Local SGD Converges Fast and Communicates Littlecited by 595
38 more
  1. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  2. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  3. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  4. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  5. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  6. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  7. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
  8. 2018RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasetscited by 148
  9. 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 140
  10. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  11. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  12. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  13. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
  14. 2021Robustness of Graph Neural Networks at Scalecited by 100
  15. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
  16. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 94
  17. 2020Differentially-Private Federated Linear Banditscited by 83
  18. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
  19. 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 66
  20. 2024Byzantine-Robust Decentralized Federated Learningcited by 47
  21. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
  22. 2021Gradient-Leakage Resilient Federated Learningcited by 40
  23. 2020Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attackscited by 32
  24. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  25. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 28
  26. 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 27
  27. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learningcited by 25
  28. 2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
  29. 2023FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMscited by 19
  30. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  31. 2023Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregationcited by 16
  32. 2021Differential Privacy Meets Federated Learning under Communication Constraintscited by 15
  33. 2024SoK: On Gradient Leakage in Federated Learningcited by 12
  34. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  35. 2023Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Thingscited by 10
  36. 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learningcited by 9
  37. 2023Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learningcited by 9
  38. 2022Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learningcited by 8

Built on by

Not cited yet.