Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning

TL;DR

This paper reveals a novel attack method that can infer private labels from aggregated gradients in federated learning, bypassing secure aggregation defenses and achieving perfect accuracy.

Contribution

It introduces a stealthy label inference attack that exploits gradient disaggregation in secure federated learning, demonstrating its effectiveness through extensive experiments.

Findings

Achieves 100% label recovery accuracy across datasets

Identifies vulnerabilities in secure aggregation protocols

Proposes a fishing model to infer client labels

Abstract

Federated Learning (FL) exhibits privacy vulnerabilities under gradient inversion attacks (GIAs), which can extract private information from individual gradients. To enhance privacy, FL incorporates Secure Aggregation (SA) to prevent the server from obtaining individual gradients, thus effectively resisting GIAs. In this paper, we propose a stealthy label inference attack to bypass SA and recover individual clients' private labels. Specifically, we conduct a theoretical analysis of label inference from the aggregated gradients that are exclusively obtained after implementing SA. The analysis results reveal that the inputs (embeddings) and outputs (logits) of the final fully connected layer (FCL) contribute to gradient disaggregation and label restoration. To preset the embeddings and logits of FCL, we craft a fishing model by solely modifying the parameters of a single batch normalization (BN) layer in the original model. Distributing client-specific fishing models, the server can derive the individual gradients regarding the bias of FCL by resolving a linear system with expected embeddings and the aggregated gradients as coefficients. Then the labels of each client can be precisely computed based on preset logits and gradients of FCL's bias. Extensive experiments show that our attack achieves large-scale label recovery with 100\% accuracy on various datasets and model architectures.