Adversarial Machine Learning-Based Anticipation of Threats Against Vehicle-to-Microgrid Services

TL;DR

This paper investigates adversarial machine learning attacks on Vehicle-to-Microgrid services, demonstrating that gray-box attacks can effectively deceive classifiers with less data than white-box attacks, highlighting vulnerabilities in edge ML systems.

Contribution

It introduces a multi-stage gray-box attack framework against V2M services and shows its effectiveness compared to white-box attacks, using real-time data collection and surrogate modeling.

Findings

Gray-box attacks can mislead classifiers with 40% less data.

K-NN was effective as a surrogate model in simulations.

Multi-stage attack achieves up to 73.2% EIR.

Abstract

In this paper, we study the expanding attack surface of Adversarial Machine Learning (AML) and the potential attacks against Vehicle-to-Microgrid (V2M) services. We present an anticipatory study of a multi-stage gray-box attack that can achieve a comparable result to a white-box attack. Adversaries aim to deceive the targeted Machine Learning (ML) classifier at the network edge to misclassify the incoming energy requests from microgrids. With an inference attack, an adversary can collect real-time data from the communication between smart microgrids and a 5G gNodeB to train a surrogate (i.e., shadow) model of the targeted classifier at the edge. To anticipate the associated impact of an adversary's capability to collect real-time data instances, we study five different cases, each representing different amounts of real-time data instances collected by an adversary. Out of six ML models trained on the complete dataset, K-Nearest Neighbour (K-NN) is selected as the surrogate model, and through simulations, we demonstrate that the multi-stage gray-box attack is able to mislead the ML classifier and cause an Evasion Increase Rate (EIR) up to 73.2% using 40% less data than what a white-box attack needs to achieve a similar EIR.