paper-with-me

홈 › Papers

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

2026-04-01 · Hao Fang, Wenbo Yu, Bin Chen, Xuan Wang, Shu-Tao Xia, Qing Liao, Ke Xu arxiv

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model by transmitting locally computed gradients to a central server without exposing their private data. Nonetheless, recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage, e.g., an attacker can invert shared gradients to reconstruct sensitive data by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. However, existing attacks simply perform gradient inversion in the latent space of the GAN model, which limits their expression ability and generalizability. To tackle these challenges, we propose \textbf{G}radient \textbf{I}nversion over \textbf{F}eature \textbf{D}omains (GIFD), which disassembles the GAN model and searches the hierarchical features of the intermediate layers. Instead of optimizing only over the initial latent code, we progressively change the optimized layer, from the initial latent space to intermediate layers closer to the output images. In addition, we design a regularizer to avoid unreal image generation by adding a small ${l_1}$ ball constraint to the searching range. We also extend GIFD to the out-of-distribution (OOD) setting, which weakens the assumption that the training sets of GANs and FL tasks obey the same data distribution. Furthermore, we consider the challenging OOD scenario of label inconsistency and propose a label mapping technique as an effective solution. Extensive experiments demonstrate that our method can achieve pixel-level reconstruction and outperform competitive baselines across a variety of FL scenarios.

📄 PDF Abstract BibTeX arXiv:2604.00955

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningImage Generation

Similar Papers 제목 키워드 기반

Enhancing Privacy against Inversion Attacks in Federated Learning by using Mixing Gradients Strategies

2022-04-26 · Shaltiel Eloul, Fran Silavong, Sanket Kamthe, Antonios Georgiadis 외

Federated learning reduces the risk of information leakage, but remains vulnerable to attacks. We investigate how several neural network design decisions can defend against gradients inversion attacks. We show that overl…

Federated Learning

Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation

2025-03-19 · Shiyi Jiang, Farshad Firouzi, Krishnendu Chakrabarty

The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses an…

Federated LearningPrivacy Preserving

Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation

2023-01-01 · ICCV 2023 1 · Guangnian Wan, Haitao Du, Xuejing Yuan, Jun Yang 외

Federated learning (FL) is a privacy-enhanced distributed machine learning framework, in which multiple clients collaboratively train a global model by exchanging their model updates without sharing local private dat…

Federated Learning

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks

2023-09-08 · Daniel Scheliga, Patrick Mäder, Marco Seeland

Gradient inversion attacks are an ubiquitous threat in federated learning as they exploit gradient leakage to reconstruct supposedly private training data. Recent work has proposed to prevent gradient leakage without los…

Federated Learningimage-classificationImage ClassificationPrivacy Preserving

GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge

2024-05-06 · Jin Qian, Kaimin Wei, Yongdong Wu, Jilian Zhang 외

Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion…

Federated LearningPrivacy Preserving