Supervised Text Classification with Leveled Homomorphic Encryption - ARCHIVED

Articles and reports: 11-522-X202100100027


Privacy concerns are a barrier to applying remote analytics, including machine learning, on sensitive data via the cloud. In this work, we use a leveled fully Homomorphic Encryption scheme to train an end-to-end supervised machine learning algorithm to classify texts while protecting the privacy of the input data points. We train our single-layer neural network on a large simulated dataset, providing a practical solution to a real-world multi-class text classification task. To improve both accuracy and training time, we train an ensemble of such classifiers in parallel using ciphertext packing.

Key Words: Privacy Preservation, Machine Learning, Encryption

Issue Number: 2021001
Author(s): Zanussi, Zachary; Santos, Benjamin; Molladavoudi, Saeid
FormatRelease dateMore information
PDFOctober 29, 2021

Related information

Subjects and keywords


Date modified: