Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

Ryo Yonetani, Vishnu Boddeti, Kris M. Kitani, Yoichi Sato
ICCV 2017 .


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 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 demonstrates that the proposed approach significantly outperforms other privacy-preserving methods and achieves comparable performance against state-of-the-art visual recognition methods without privacy preservation.