HOLMES: Efficient Distribution Testing for Secure Collaborative Learning


Ian Chang and Katerina Sotiraki, UC Berkeley; Weikeng Chen, UC Berkeley & DZK Labs; Murat Kantarcioglu, University of Texas at Dallas & UC Berkeley; Raluca Popa, UC Berkeley


Using secure multiparty computation (MPC), organizations which own sensitive data (e.g., in healthcare, finance or law enforcement) can train machine learning models over their joint dataset without revealing their data to each other. At the same time, secure computation restricts operations on the joint dataset, which impedes computation to assess its quality. Without such an assessment, deploying a jointly trained model is potentially illegal. Regulations, such as the European Union's General Data Protection Regulation (GDPR), require organizations to be legally responsible for the errors, bias, or discrimination caused by their machine learning models. Hence, testing data quality emerges as an indispensable step in secure collaborative learning. However, performing distribution testing is prohibitively expensive using current techniques, as shown in our experiments.

We present HOLMES, a protocol for performing distribution testing efficiently. In our experiments, compared with three non-trivial baselines, HOLMES achieves a speedup of more than 10× for classical distribution tests and up to 104× for multidimensional tests. The core of HOLMES is a hybrid protocol that integrates MPC with zero-knowledge proofs and a new ZK-friendly and naturally oblivious sketching algorithm for multidimensional tests, both with significantly lower computational complexity and concrete execution costs.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

@inproceedings {287314,
author = {Ian Chang and Katerina Sotiraki and Weikeng Chen and Murat Kantarcioglu and Raluca Popa},
title = {{HOLMES}: Efficient Distribution Testing for Secure Collaborative Learning},
booktitle = {32nd USENIX Security Symposium (USENIX Security 23)},
year = {2023},
isbn = {978-1-939133-37-3},
address = {Anaheim, CA},
pages = {4823--4840},
url = {https://www.usenix.org/conference/usenixsecurity23/presentation/chang},
publisher = {USENIX Association},
month = aug

Presentation Video