English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning-based automatic modulation classification (AMC) models aresusceptible to adversarial attacks. Such attacks inject specifically craftedwireless interference into transmitted signals to induce erroneousclassification predictions. Furthermore, adversarial interference istransferable in black box environments, allowing an adversary to attackmultiple deep learning models with a single perturbation crafted for aparticular classification model. In this work, we propose a novel wirelessreceiver architecture to mitigate the effects of adversarial interference invarious black box attack environments. We begin by evaluating the architectureuncertainty environment, where we show that adversarial attacks crafted to foolspecific AMC DL architectures are not directly transferable to different DLarchitectures. Next, we consider the domain uncertainty environment, where weshow that adversarial attacks crafted on time domain and frequency domainfeatures to not directly transfer to the altering domain. Using these insights,we develop our Assorted Deep Ensemble (ADE) defense, which is an ensemble ofdeep learning architectures trained on time and frequency domainrepresentations of received signals. Through evaluation on two wireless signaldatasets under different sources of uncertainty, we demonstrate that our ADEobtains substantial improvements in AMC classification performance comparedwith baseline defenses across different adversarial attacks and potencies.

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