Secure CNN Computation Using Random Projection and Support Vector Regression

Abstract

Convolutional Neural Networks (CNNs) are foundational in numerous machine learning applications, particularly in image processing, where they excel in identifying patterns within visual data. At the core of CNNs lies the 2D convolution operation, which is essential for extracting spatial features from images. However, when applied to sensitive data, such as in medical imaging or surveillance, preserving the privacy of both the input data and the convolutional filters is crucial. This paper introduces a novel approach to secure the 2D convolution operation in CNNs, leveraging random projection and machine learning techniques. By encrypting the input images and convolutional filters using random projection, the method ensures that the convolution feature maps are computed securely without exposing the underlying data. The proposed technique maintains the accuracy and efficiency of CNN while offering a privacy-preserving solution that is more computationally efficient than traditional methods such as Homomorphic Encryption (HE). Experimental results using synthetic Gaussian data demonstrate the feasibility and effectiveness of this approach in securely computing convolutions, making it a promising solution for protecting sensitive information in CNN-based applications. Additionally, the paper compares the proposed method with homomorphic encryption, showing that while both methods ensure data confidentiality, the random projection approach offers a more efficient solution with lower computational overhead.