A Practical Adversarial Attack on Contingency Detection of Smart Energy Systems
This work addresses a critical security gap in smart energy systems, which is an incremental step as adversarial attacks are well-studied in other domains but not in energy systems.
The authors tackled the vulnerability of deep learning-based smart energy systems to adversarial attacks by proposing a novel attack model that compromises dynamical controls, and they optimized its deployment using deep reinforcement learning, achieving evaluation on a standard IEEE 9-bus system.
Due to the advances in computing and sensing, deep learning (DL) has widely been applied in smart energy systems (SESs). These DL-based solutions have proved their potentials in improving the effectiveness and adaptiveness of the control systems. However, in recent years, increasing evidence shows that DL techniques can be manipulated by adversarial attacks with carefully-crafted perturbations. Adversarial attacks have been studied in computer vision and natural language processing. However, there is very limited work focusing on the adversarial attack deployment and mitigation in energy systems. In this regard, to better prepare the SESs against potential adversarial attacks, we propose an innovative adversarial attack model that can practically compromise dynamical controls of energy system. We also optimize the deployment of the proposed adversarial attack model by employing deep reinforcement learning (RL) techniques. In this paper, we present our first-stage work in this direction. In simulation section, we evaluate the performance of our proposed adversarial attack model using standard IEEE 9-bus system.