Fast Privacy-Preserving Text Classification based on Secure Multiparty Computation

TY - JOUR

T1 - Fast Privacy-Preserving Text Classification based on Secure Multiparty Computation

AU - Davi Resende, Amanda C.

AU - Railsback, Davis

AU - Dowsley, Rafael

AU - Nascimento, Anderson C A

AU - Aranha, Diego F.

N1 - Publisher Copyright: © 2005-2012 IEEE.

PY - 2022

Y1 - 2022

N2 - We propose a privacy-preserving Naive Bayes classifier and apply it to the problem of private text classification. In this setting, a party (Alice) holds a text message, while another party (Bob) holds a classifier. At the end of the protocol, Alice will only learn the result of the classifier applied to her text input and Bob learns nothing. Our solution is based on Secure Multiparty Computation (SMC). Our Rust implementation provides a fast and secure solution for the classification of unstructured text. Applying our solution to the case of spam detection (the solution is generic, and can be used in any other scenario in which the Naive Bayes classifier can be employed), we can classify an SMS as spam or ham in less than 340ms in the case where the dictionary size of Bob's model includes all words (n = 5200) and Alice's SMS has at most m = 160 unigrams. In the case with n = 369 and m = 8 (the average of a spam SMS in the database), our solution takes only 21ms.

AB - We propose a privacy-preserving Naive Bayes classifier and apply it to the problem of private text classification. In this setting, a party (Alice) holds a text message, while another party (Bob) holds a classifier. At the end of the protocol, Alice will only learn the result of the classifier applied to her text input and Bob learns nothing. Our solution is based on Secure Multiparty Computation (SMC). Our Rust implementation provides a fast and secure solution for the classification of unstructured text. Applying our solution to the case of spam detection (the solution is generic, and can be used in any other scenario in which the Naive Bayes classifier can be employed), we can classify an SMS as spam or ham in less than 340ms in the case where the dictionary size of Bob's model includes all words (n = 5200) and Alice's SMS has at most m = 160 unigrams. In the case with n = 369 and m = 8 (the average of a spam SMS in the database), our solution takes only 21ms.

KW - Naive Bayes

KW - Privacy-preserving classification

KW - secure multiparty computation

KW - spam

U2 - 10.1109/TIFS.2022.3144007

DO - 10.1109/TIFS.2022.3144007

M3 - Journal article

SN - 1556-6013

VL - 17

SP - 428

EP - 442

JO - IEEE Transactions on Information Forensics and Security

JF - IEEE Transactions on Information Forensics and Security

ER -