AuditML: An Efficient Publicly Auditable Privacy-Preserving Framework for Machine Learning Inference

Summary

AuditML is a publicly auditable privacy-preserving framework for machine learning inference in the semi-honest model. It combines arithmetic secret sharing with commitment-based audit data, implemented on MP-SPDZ, and evaluated on linear regression, fixed-threshold binary logistic classification, and linear-kernel SVM. At a batch size of 50, linear and logistic inference completed online in under one second, while SVM took 10.0939–40.0334 seconds.