Adversarial ML Attack on Self Organizing Cellular Networks

TL;DR

This paper investigates the vulnerability of deep neural network-based self-organizing networks (SON) to adversarial attacks, demonstrating potential risks and providing explanations for misclassifications using explainable AI techniques.

Contribution

It is the first to evaluate and explain the robustness of SON against adversarial examples, highlighting security concerns in DNN-based cellular network automation.

Findings

SON is vulnerable to adversarial attacks on DNNs

Explainable AI can elucidate reasons for misclassification

Adversarial robustness is critical for reliable SON deployment

Abstract

Deep Neural Networks (DNN) have been widely adopted in self-organizing networks (SON) for automating different networking tasks. Recently, it has been shown that DNN lack robustness against adversarial examples where an adversary can fool the DNN model into incorrect classification by introducing a small imperceptible perturbation to the original example. SON is expected to use DNN for multiple fundamental cellular tasks and many DNN-based solutions for performing SON tasks have been proposed in the literature have not been tested against adversarial examples. In this paper, we have tested and explained the robustness of SON against adversarial example and investigated the performance of an important SON use case in the face of adversarial attacks. We have also generated explanations of incorrect classifications by utilizing an explainable artificial intelligence (AI) technique.