Outsourcing Private Machine Learning via Lightweight Secure Arithmetic Computation
This work addresses privacy concerns in collaborative settings like healthcare, where parties need to perform inference on private data using public models, offering a solution against malicious deviations, though it is incremental by focusing on active security over prior passive approaches.
The paper tackles the problem of securely outsourcing private machine learning computations in the presence of active adversaries, proposing an actively secure protocol and demonstrating its efficiency on real-world neural network tasks, such as collaborative disease prediction.
In several settings of practical interest, two parties seek to collaboratively perform inference on their private data using a public machine learning model. For instance, several hospitals might wish to share patient medical records for enhanced diagnostics and disease prediction, but may not be able to share data in the clear because of privacy concerns. In this work, we propose an actively secure protocol for outsourcing secure and private machine learning computations. Recent works on the problem have mainly focused on passively secure protocols, whose security holds against passive (`semi-honest') parties but may completely break down in the presence of active (`malicious') parties who can deviate from the protocol. Secure neural networks based classification algorithms can be seen as an instantiation of an arithmetic computation over integers. We showcase the efficiency of our protocol by applying it to real-world instances of arithmetized neural network computations, including a network trained to perform collaborative disease prediction.