Encrypted Visual Feedback Control Using RLWE-Based Cryptosystem

TL;DR

This paper introduces an encrypted visual feedback control method that performs feature extraction and control computations directly on encrypted images using RLWE encryption, enhancing data privacy in control systems.

Contribution

It presents a novel RLWE-based encryption algorithm enabling encrypted visual feedback control with reduced computational cost and maintains data privacy throughout the process.

Findings

The framework successfully performs control tasks on encrypted images.

Encryption reduces computational cost via message packing.

Numerical simulations demonstrate the effectiveness of the approach.

Abstract

This study proposes an encrypted visual feedback control algorithm for regulating a one-dimensional stage using Ring Learning With Errors (RLWE) encryption. The proposed algorithm performs both feature extraction and controller computations directly on encrypted images, ensuring that sensitive visual data remain protected throughout the entire control process. Furthermore, an image captured by the camera is encrypted into a single ciphertext leveraging the message packing technique of RLWE encryption, thereby reducing computational cost. The effectiveness of the proposed framework is demonstrated through numerical simulations.