Paper 2021/1517

HOLMES: Efficient Distribution Testing for Secure Collaborative Learning

Ian Chang, UC Berkeley
Katerina Sotiraki, UC Berkeley
Weikeng Chen, UC Berkeley, DZK Labs
Murat Kantarcioglu, University of Texas at Dallas, UC Berkeley
Raluca Ada 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 10x for classical distribution tests and up to 10^4x 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.

Available format(s)
Publication info
Published elsewhere. USENIX Security 2023
secure collaborative learningmultiparty computationmalicious security
Contact author(s)
iac @ berkeley edu
katesot @ berkeley edu
w k @ berkeley edu
muratk @ utdallas edu
raluca popa @ berkeley edu
2023-03-06: revised
2021-11-20: received
See all versions
Short URL
Creative Commons Attribution


      author = {Ian Chang and Katerina Sotiraki and Weikeng Chen and Murat Kantarcioglu and Raluca Ada Popa},
      title = {HOLMES: Efficient Distribution Testing for Secure Collaborative Learning},
      howpublished = {Cryptology ePrint Archive, Paper 2021/1517},
      year = {2021},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.