An Adversarial Approach to Evaluating the Robustness of Event Identification Models
This addresses security vulnerabilities in power grid event detection, but is incremental as it applies existing adversarial testing methods to a specific domain.
The paper evaluated the robustness of event identification models for power systems against adversarial attacks, finding that logistic regression was more susceptible than gradient boosting in tests on a synthetic 500-bus system.
Intelligent machine learning approaches are finding active use for event detection and identification that allow real-time situational awareness. Yet, such machine learning algorithms have been shown to be susceptible to adversarial attacks on the incoming telemetry data. This paper considers a physics-based modal decomposition method to extract features for event classification and focuses on interpretable classifiers including logistic regression and gradient boosting to distinguish two types of events: load loss and generation loss. The resulting classifiers are then tested against an adversarial algorithm to evaluate their robustness. The adversarial attack is tested in two settings: the white box setting, wherein the attacker knows exactly the classification model; and the gray box setting, wherein the attacker has access to historical data from the same network as was used to train the classifier, but does not know the classification model. Thorough experiments on the synthetic South Carolina 500-bus system highlight that a relatively simpler model such as logistic regression is more susceptible to adversarial attacks than gradient boosting.