Electro-Magnetic Side-Channel Attack Through Learned Denoising and Classification

TL;DR

This paper introduces a deep learning-based electromagnetic side-channel attack system that reconstructs intercepted data in real-time and includes a protective alarm mechanism, achieving over 57% character recovery and 95% alarm accuracy.

Contribution

It presents a novel real-time side-channel attack method using deep learning and character recognition, with an integrated protection system for enhanced security.

Findings

Over 57% of characters recovered from signals

Alarm system with over 95% success rate

Applicable to analog and digital signals

Abstract

This paper proposes an upgraded electro-magnetic side-channel attack that automatically reconstructs the intercepted data. A novel system is introduced, running in parallel with leakage signal interception and catching compromising data in real-time. Based on deep learning and character recognition the proposed system retrieves more than 57% of characters present in intercepted signals regardless of signal type: analog or digital. The approach is also extended to a protection system that triggers an alarm if the system is compromised, demonstrating a success rate over 95%. Based on software-defined radio and graphics processing unit architectures, this solution can be easily deployed onto existing information systems where information shall be kept secret.