Secure Data Sharing With Flow Model
This addresses privacy concerns in multi-party computation for ML, offering a solution for secure collaborative training, though it appears incremental as it builds on existing encryption and flow model techniques.
The paper tackles secure data sharing for machine learning by proposing a rotation-based method using flow models to encrypt data, preventing recovery by other parties while enabling joint training. The method is demonstrated in supervised and unsupervised scenarios, with theoretical security justification and code availability.
In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training purposes, but the data are also encrypted so that they cannot be recovered by other parties. We present a rotation based method using flow model, and theoretically justified its security. We demonstrate the effectiveness of our method in different scenarios, including supervised secure model training, and unsupervised generative model training. Our code is available at https://github.com/ duchenzhuang/flowencrypt.