Generative Adversarial Networks to Secure Vehicle-to-Microgrid Services

As the use of Artificial Intelligence (AI) becomes more prevalent in the cyber-physical systems, there has been a rise in the number of adversarial attacks targeting Machine Learning (ML) models. Therefore, it has become imperative to safeguard ML models against such attacks. Our analysis under a vehicle-to-microgrid service setting shows that adversaries aim to deceive the victim's ML classifier at the network edge to misclassify the incoming energy requests from microgrid users. In this paper, we introduce an AI-powered framework to detect new instances of Adversarial attacks against Vehicle-to-Microgrid (V2M) systems. The proposed detection technique uses a Generative Adversarial Network (GAN) model and ML classifiers to accurately detect adversarial attacks. We test the proposed detection technique under three strategies of adversarial sample generation. Adversaries perform a two-stage adversarial attack beginning with an inference attack followed by an evasion attack against the victim's ML model. In addition, we investigate how the adversaries' knowledge of the victim's ML training dataset impacts the Adversarial Detection Rate (ADR). We assess five access cases to the victim's ML training dataset varying from a white-box to various levels of a gray-box attack. Moreover, we implement an unsupervised ML algorithm (i.e., DBSCAN) as a baseline method. Through simulations, we show that DBSCAN results in an ADR up to 69% and 17% for gray-box and white-box attacks, respectively. On the other hand, our proposed generative approach (i.e., GAN-based) outperforms DBSCAN resulting in an ADR up to 94.6% for the gray-box attack and 30.2% for the white-box attack.