Kaiyuan Zhang (Purdue University), Siyuan Cheng (Purdue University), Guangyu Shen (Purdue University), Bruno Ribeiro (Purdue University), Shengwei An (Purdue University), Pin-Yu Chen (IBM Research AI), Xiangyu Zhang (Purdue University), Ninghui Li (Purdue University)

Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data.
The process of sending these model updates may leak client's private data information.
Existing gradient inversion attacks can exploit this vulnerability to recover private training instances from a client's gradient vectors. Recently, researchers have proposed advanced gradient inversion techniques that existing defenses struggle to handle effectively.
In this work, we present a novel defense tailored for large neural network models. Our defense capitalizes on the high dimensionality of the model parameters to perturb gradients within a textit{subspace orthogonal} to the original gradient. By leveraging cold posteriors over orthogonal subspaces, our defense implements a refined gradient update mechanism. This enables the selection of an optimal gradient that not only safeguards against gradient inversion attacks but also maintains model utility.
We conduct comprehensive experiments across three different datasets and evaluate our defense against various state-of-the-art attacks and defenses.

View More Papers

Hidden and Lost Control: on Security Design Risks in...

Haoqiang Wang, Yiwei Fang (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences; Indiana University Bloomington), Yichen Liu (Indiana University Bloomington), Ze Jin (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences; Indiana University Bloomington), Emma Delph…

Read More

SCRUTINIZER: Towards Secure Forensics on Compromised TrustZone

Yiming Zhang (Southern University of Science and Technology and The Hong Kong Polytechnic University), Fengwei Zhang (Southern University of Science and Technology), Xiapu Luo (The Hong Kong Polytechnic University), Rui Hou (Institute of Information Engineering, Chinese Academy of Sciences), Xuhua Ding (Singapore Management University), Zhenkai Liang (National University of Singapore), Shoumeng Yan (Ant Group), Tao…

Read More

Delay-allowed Differentially Private Data Stream Release

Xiaochen Li (University of Virginia), Zhan Qin (Zhejiang University), Kui Ren (Zhejiang University), Chen Gong (University of Virginia), Shuya Feng (University of Connecticut), Yuan Hong (University of Connecticut), Tianhao Wang (University of Virginia)

Read More

The Discriminative Power of Cross-layer RTTs in Fingerprinting Proxy...

Diwen Xue (University of Michigan), Robert Stanley (University of Michigan), Piyush Kumar (University of Michigan), Roya Ensafi (University of Michigan)

Read More