TripleBlind: A Privacy-Preserving Framework for Decentralized Data and Algorithms
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:343-348, 2022.
Centralized sharing of sensitive data for training and inference is challenging and undesired due to privacy, competition, and legal concerns. While distributed learning and secure inference have demonstrated significant privacy gains, these methods still largely ignore the design and implementation of practical, privacy-preserving tool support. To address these challenges, we present TripleBlind, an automated privacy-preserving framework for creating and consuming data-driven applications from decentralized data and algorithms. TripleBlind provides a set of automated, high-level APIs that enable (1) extracting knowledge from remote data without moving it outside the owner’s infrastructure, (2) training AI models from decentralized data, and (3) consuming trained models for secure inference-as-a-service; all without compromising the privacy of either the model/query or the data. In this short paper, we shed light on the underlying training and inference methods, the design and implementation of our framework, and showcase the actual code necessary to run a secure, remote inference using our secure multi-party computation API. A video demo highlighting the main features of our framework is located at www.tripleblind.ai/neurips2021