Towards General Deep Leakage in Federated Learning

2021-10-18 · Jiahui Geng, Yongli Mou, Feifei Li, Qing Li, Oya Beyan, Stefan Decker, Chunming Rong

Unlike traditional central training, federated learning (FL) improves the performance of the global model by sharing and aggregating local models rather than local data to protect the users' privacy. Although this training approach appears secure, some research has demonstrated that an attacker can still recover private data based on the shared gradient information. This on-the-fly reconstruction attack deserves to be studied in depth because it can occur at any stage of training, whether at the beginning or at the end of model training; no relevant dataset is required and no additional models need to be trained. We break through some unrealistic assumptions and limitations to apply this reconstruction attack in a broader range of scenarios. We propose methods that can reconstruct the training data from shared gradients or weights, corresponding to the FedSGD and FedAvg usage scenarios, respectively. We propose a zero-shot approach to restore labels even if there are duplicate labels in the batch. We study the relationship between the label and image restoration. We find that image restoration fails even if there is only one incorrectly inferred label in the batch; we also find that when batch images have the same label, the corresponding image is restored as a fusion of that class of images. Our approaches are evaluated on classic image benchmarks, including CIFAR-10 and ImageNet. The batch size, image quality, and the adaptability of the label distribution of our approach exceed those of GradInversion, the state-of-the-art.

📄 PDF Abstract BibTeX arXiv:2110.09074

Code (1)

hangyuzhu/leakage-attack-in-federated-learning pytorch

Tasks

Federated Learning Image RestorationReconstruction Attack

FEDLAD: Federated Evaluation of Deep Leakage Attacks and Defenses

2024-11-05 · Isaac Baglin, Xiatian Zhu, Simon Hadfield

Federated Learning is a privacy preserving decentralized machine learning paradigm designed to collaboratively train models across multiple clients by exchanging gradients to the server and keeping private data local. Ne…

Federated Learning Privacy Preserving

GEN-Guard: Correcting Generalization Failures for Deployable Federated Surgical AI

2026-06-18 · Julia Alekseenko, Pietro Mascagni, AI4SafeChole Consortium, Nicolas Padoy arxiv

Federated Learning (FL) in surgical video AI enables collaborative model training without sharing sensitive data. However, standard evaluation practices - selecting the "best" global model based only on validation data f…

Surgical phase recognition Zero-shot Generalization Federated Learning Polyp Segmentation

Gradient-Leakage Resilient Federated Learning

2021-07-02 · Wenqi Wei, Ling Liu, Yanzhao Wu, Gong Su 외

Federated learning(FL) is an emerging distributed learning paradigm with default client privacy because clients can keep sensitive data on their devices and only share local training parameter updates with the federated …

Federated Learning Privacy Preserving

Catastrophic Data Leakage in Vertical Federated Learning

2021-12-01 · NeurIPS 2021 12 · Xiao Jin, Pin-Yu Chen, Chia-Yi Hsu, Chia-Mu Yu 외

Recent studies show that private training data can be leaked through the gradients sharing mechanism deployed in distributed machine learning systems, such as federated learning (FL). Increasing batch size to complicate …

Federated Learning Vertical Federated Learning

CAFE: Catastrophic Data Leakage in Vertical Federated Learning

2021-10-26 · Xiao Jin, Pin-Yu Chen, Chia-Yi Hsu, Chia-Mu Yu 외