TripleBlind: A Privacy-Preserving Framework for Decentralized Data and Algorithms

Gharib Gharibi, Babak Poorebrahim Gilkalaye, Ravi Patel, Andrew Rademacher, David Wagner, Jack Fay, Gary Moore, Steve Penrod, Greg Storm, Riddhiman Das
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:343-348, 2022.

Abstract

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

Cite this Paper


BibTeX
@InProceedings{pmlr-v176-gharibi22a, title = {TripleBlind: A Privacy-Preserving Framework for Decentralized Data and Algorithms}, author = {Gharibi, Gharib and Poorebrahim Gilkalaye, Babak and Patel, Ravi and Rademacher, Andrew and Wagner, David and Fay, Jack and Moore, Gary and Penrod, Steve and Storm, Greg and Das, Riddhiman}, booktitle = {Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track}, pages = {343--348}, year = {2022}, editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara}, volume = {176}, series = {Proceedings of Machine Learning Research}, month = {06--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v176/gharibi22a/gharibi22a.pdf}, url = {https://proceedings.mlr.press/v176/gharibi22a.html}, abstract = {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 } }
Endnote
%0 Conference Paper %T TripleBlind: A Privacy-Preserving Framework for Decentralized Data and Algorithms %A Gharib Gharibi %A Babak Poorebrahim Gilkalaye %A Ravi Patel %A Andrew Rademacher %A David Wagner %A Jack Fay %A Gary Moore %A Steve Penrod %A Greg Storm %A Riddhiman Das %B Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track %C Proceedings of Machine Learning Research %D 2022 %E Douwe Kiela %E Marco Ciccone %E Barbara Caputo %F pmlr-v176-gharibi22a %I PMLR %P 343--348 %U https://proceedings.mlr.press/v176/gharibi22a.html %V 176 %X 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
APA
Gharibi, G., Poorebrahim Gilkalaye, B., Patel, R., Rademacher, A., Wagner, D., Fay, J., Moore, G., Penrod, S., Storm, G. & Das, R.. (2022). TripleBlind: A Privacy-Preserving Framework for Decentralized Data and Algorithms. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, in Proceedings of Machine Learning Research 176:343-348 Available from https://proceedings.mlr.press/v176/gharibi22a.html.

Related Material