Multi-Antenna Data-Driven Eavesdropping Attacks and Symbol-Level Precoding Countermeasures

TL;DR

This paper demonstrates that multi-antenna systems are vulnerable to machine learning-based eavesdropping attacks and proposes symbol-level precoding countermeasures that enhance security without impairing legitimate communication.

Contribution

It introduces ML-based eavesdropping frameworks and two novel SLP-based countermeasures to improve security in MU-MISO systems against such attacks.

Findings

ML attacks can accurately decode messages in MU-MISO systems.

Countermeasures effectively increase eavesdropper's error rate.

Security gains do not compromise legitimate users' performance.

Abstract

In this work, we consider secure communications in wireless multi-user (MU) multiple-input single-output (MISO) systems with channel coding in the presence of a multi-antenna eavesdropper (Eve). In this setting, we exploit machine learning (ML) tools to design soft and hard decoding schemes by using precoded pilot symbols as training data. In this context, we propose ML frameworks for decoders that allow an Eve to determine the transmitted message with high accuracy. We thereby show that MU-MISO systems are vulnerable to such eavesdropping attacks even when relatively secure transmission techniques are employed, such as symbol-level precoding (SLP). To counteract this attack, we propose two novel SLP-based schemes that increase the bit-error rate at Eve by impeding the learning process. We design these two security-enhanced schemes to meet different requirements regarding complexity, security, and power consumption. Simulation results validate both the ML-based eavesdropping attacks as well as the countermeasures, and show that the gain in security is achieved without affecting the decoding performance at the intended users.