DeepAI AI Chat
Log In Sign Up

DPAUC: Differentially Private AUC Computation in Federated Learning

by   Jiankai Sun, et al.
ByteDance Inc.

Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. The prior work on FL has mostly studied how to protect label privacy during model training. However, model evaluation in FL might also lead to potential leakage of private label information. In this work, we propose an evaluation algorithm that can accurately compute the widely used AUC (area under the curve) metric when using the label differential privacy (DP) in FL. Through extensive experiments, we show our algorithms can compute accurate AUCs compared to the ground truth.


page 1

page 2

page 3

page 4


Differentially Private AUC Computation in Vertical Federated Learning

Federated learning has gained great attention recently as a privacy-enha...

Differentially Private Vertical Federated Learning

A successful machine learning (ML) algorithm often relies on a large amo...

When the Curious Abandon Honesty: Federated Learning Is Not Private

In federated learning (FL), data does not leave personal devices when th...

Federated Domain Adaptation for ASR with Full Self-Supervision

Cross-device federated learning (FL) protects user privacy by collaborat...

Training Production Language Models without Memorizing User Data

This paper presents the first consumer-scale next-word prediction (NWP) ...

Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy

Deep neural networks have strong capabilities of memorizing the underlyi...