mlsanityData to 14 Oct 2026

A New Federated Learning Framework Against Gradient Inversion Attacks

arXiv 2412.07187 ↗First posted 10 Dec 2024cs.LG cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively ``breaks the direct connection'' between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL. Code is available at https://github.com/Pengxin-Guo/HyperFL.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 12 of its 91 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

12 of 91 references.

References · 12

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  2. 2016An overview of gradient descent optimization algorithmscited by 1,033
  3. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  4. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  5. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  6. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  7. 2020Provable Defense against Privacy Leakage in Federated Learning from Representation Perspectivecited by 94
  8. 2024Selective Aggregation for Low-Rank Adaptation in Federated Learningcited by 80
  9. 2020A Framework for Evaluating Gradient Leakage Attacks in Federated Learningcited by 64
  10. 2018CINIC-10 is not ImageNet or CIFAR-10cited by 7
  11. 2023Gradient Leakage Defense with Key-Lock Module for Federated Learningcited by 4
  12. 2023Temporal Gradient Inversion Attacks with Robust Optimizationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  2. 2025FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Modelscited by 6
  3. 2025Exploring Federated Pruning for Large Language Modelscited by 2
  4. 2025Multi-Hop Privacy Propagation for Differentially Private Federated Learning in Social Networkscited by 0
  5. 2025Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learningcited by 0
  6. 2026Rethinking Generative Reconstruction Attacks against Graph Neural Network Modelscited by 0