A Deep Ensemble-based Wireless Receiver Architecture for Mitigating Adversarial Attacks in Automatic Modulation Classification

TL;DR

This paper introduces a deep ensemble-based wireless receiver architecture called ADE that effectively mitigates adversarial attacks in automatic modulation classification by leveraging uncertainty and domain diversity.

Contribution

The paper proposes the ADE ensemble architecture, which enhances robustness against adversarial attacks in AMC by training on diverse domain representations and evaluating transferability.

Findings

ADE significantly improves classification accuracy under adversarial attacks.

Adversarial attacks are less transferable across different architectures and domains.

The approach outperforms baseline defenses on multiple datasets.

Abstract

Deep learning-based automatic modulation classification (AMC) models are susceptible to adversarial attacks. Such attacks inject specifically crafted wireless interference into transmitted signals to induce erroneous classification predictions. Furthermore, adversarial interference is transferable in black box environments, allowing an adversary to attack multiple deep learning models with a single perturbation crafted for a particular classification model. In this work, we propose a novel wireless receiver architecture to mitigate the effects of adversarial interference in various black box attack environments. We begin by evaluating the architecture uncertainty environment, where we show that adversarial attacks crafted to fool specific AMC DL architectures are not directly transferable to different DL architectures. Next, we consider the domain uncertainty environment, where we show that adversarial attacks crafted on time domain and frequency domain features to not directly transfer to the altering domain. Using these insights, we develop our Assorted Deep Ensemble (ADE) defense, which is an ensemble of deep learning architectures trained on time and frequency domain representations of received signals. Through evaluation on two wireless signal datasets under different sources of uncertainty, we demonstrate that our ADE obtains substantial improvements in AMC classification performance compared with baseline defenses across different adversarial attacks and potencies.