Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

TL;DR

This paper introduces a novel privacy-preserving framework for visual learning that uses a new encryption scheme called doubly-permuted homomorphic encryption, enabling secure aggregation of classifiers with high-dimensional sparse data.

Contribution

The paper presents DPHE, an efficient encryption scheme for privacy-preserving visual learning that reduces computational costs for high-dimensional sparse data.

Findings

Achieves comparable accuracy to non-private methods

Significantly outperforms existing privacy-preserving techniques

Maintains privacy during classifier aggregation

Abstract

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and to ensure that no private information about the data is exposed during and after its learning procedure. We utilize a homomorphic cryptosystem that can aggregate the local classifiers while they are encrypted and thus kept secret. To overcome the high computational cost of homomorphic encryption of high-dimensional classifiers, we (1) impose sparsity constraints on local classifier updates and (2) propose a novel efficient encryption scheme named doubly-permuted homomorphic encryption (DPHE) which is tailored to sparse high-dimensional data. DPHE (i) decomposes sparse data into its constituent non-zero values and their corresponding support indices, (ii) applies homomorphic encryption only to the non-zero values, and (iii) employs double permutations on the support indices to make them secret. Our experimental evaluation on several public datasets shows that the proposed approach achieves comparable performance against state-of-the-art visual recognition methods while preserving privacy and significantly outperforms other privacy-preserving methods.