.png){kind=icon}
Return
Encrypted Image Classification with Low Memory Footprint Using Fully Homomorphic Encryption
.png){kind=icon}
OA
AI
DOI：10.1142/S0129065724500254.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Classifying images has become a straightforward and accessible task, thanks to the advent of Deep Neural Networks. Nevertheless, not much attention is given to the privacy concerns associated with sensitive data contained in images. In this study, we propose a solution to this issue by exploring an intersection between Machine Learning and cryptography. In particular, Fully Homomorphic Encryption (FHE) emerges as a promising solution, as it enables computations to be performed on encrypted data. We therefore propose a Residual Network implementation based on FHE which allows the classification of encrypted images, ensuring that only the user can see the result. We suggest a circuit which reduces the memory requirements by more than 85% compared to the most recent works, while maintaining a high level of accuracy and a short computational time. We implement the circuit using the well-known Cheon-Kim-Kim-Song (CKKS) scheme, which enables approximate encrypted computations. We evaluate the results from three perspectives: memory requirements, computational time and calculations precision. We demonstrate that it is possible to evaluate an encrypted ResNet20 in less than five minutes on a laptop using approximately 15GB of memory, achieving an accuracy of 91.67% on the CIFAR-10 dataset, which is almost equivalent to the accuracy of the plain model (92.60%).
Keywords:
Encrypted neural network
secure machine learning
homomorphic encryption
Journal
IF:
6.4
Papers:
1.2K
Citations:
3.3K
Organization
Cited Papers
ShareSaveShareSavePrivacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSave
View more