DPMLBench: Holistic Evaluation of Differentially Private Machine Learning

Chengkun Wei, Minghu Zhao, Zhikun Zhang, Min Chen, Wenlong Meng, Bo Liu, Yuan Fan, Wenzhi Chen

Research output: Working paper / PreprintPreprintAcademic

5 Downloads (Pure)

Abstract

Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful machine learning techniques, differentially private machine learning (DPML) is increasingly important. As the most classic DPML algorithm, DP-SGD incurs a significant loss of utility, which hinders DPML's deployment in practice. Many studies have recently proposed improved algorithms based on DP-SGD to mitigate utility loss. However, these studies are isolated and cannot comprehensively measure the performance of improvements proposed in algorithms. More importantly, there is a lack of comprehensive research to compare improvements in these DPML algorithms across utility, defensive capabilities, and generalizability. We fill this gap by performing a holistic measurement of improved DPML algorithms on utility and defense capability against membership inference attacks (MIAs) on image classification tasks. We first present a taxonomy of where improvements are located in the machine learning life cycle. Based on our taxonomy, we jointly perform an extensive measurement study of the improved DPML algorithms. We also cover state-of-the-art label differential privacy (Label DP) algorithms in the evaluation. According to our empirical results, DP can effectively defend against MIAs, and sensitivity-bounding techniques such as per-sample gradient clipping play an important role in defense. We also explore some improvements that can maintain model utility and defend against MIAs more effectively. Experiments show that Label DP algorithms achieve less utility loss but are fragile to MIAs. To support our evaluation, we implement a modular re-usable software, DPMLBench, which enables sensitive data owners to deploy DPML algorithms and serves as a benchmark tool for researchers and practitioners.
Original languageEnglish
PublisherarXiv
Pages1-23
Number of pages23
DOIs
Publication statusPublished - 14 Oct 2023

Bibliographical note

To appear in the ACM Conference on Computer and Communications Security (CCS), November 2023, Tivoli Congress Center, Copenhagen, Denmark

Keywords

  • cs.LG
  • cs.CR
  • cs.CV

Fingerprint

Dive into the research topics of 'DPMLBench: Holistic Evaluation of Differentially Private Machine Learning'. Together they form a unique fingerprint.

Cite this