Search Results for author: Kailang Ma

Found 2 papers, 2 papers with code

GI-PIP: Do We Require Impractical Auxiliary Dataset for Gradient Inversion Attacks?

1 code implementation • 22 Jan 2024 • Yu Sun, Gaojian Xiong, Xianxun Yao, Kailang Ma, Jian Cui

Deep gradient inversion attacks expose a serious threat to Federated Learning (FL) by accurately recovering private data from shared gradients.

Anomaly Detection Federated Learning

Paper
Code

Instance-wise Batch Label Restoration via Gradients in Federated Learning

1 code implementation • International Conference on Learning Representations 2023 • Kailang Ma, Yu Sun, Jian Cui, Dawei Li, Zhenyu Guan and Jianwei Liu

Furthermore, we demonstrate that our method facilitates the existing gradient inversion attacks by exploiting the recovered labels, with an increase of 6-7 in PSNR on both MNIST and CIFAR100.

Federated Learning

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.