Continual Adversarial Reinforcement Learning (CARL) of False Data Injection detection: forgetting and explainability
This addresses security issues in smart inverters for renewable energy systems, but it is incremental as it builds on existing adversarial and continual learning methods.
The paper tackled the vulnerability of data-based false data injection attack (FDIA) detection methods to adversarial examples crafted via reinforcement learning, and proposed a continual adversarial RL (CARL) approach to improve detection by addressing catastrophic forgetting through joint training on all generated scenarios.
False data injection attacks (FDIAs) on smart inverters are a growing concern linked to increased renewable energy production. While data-based FDIA detection methods are also actively developed, we show that they remain vulnerable to impactful and stealthy adversarial examples that can be crafted using Reinforcement Learning (RL). We propose to include such adversarial examples in data-based detection training procedure via a continual adversarial RL (CARL) approach. This way, one can pinpoint the deficiencies of data-based detection, thereby offering explainability during their incremental improvement. We show that a continual learning implementation is subject to catastrophic forgetting, and additionally show that forgetting can be addressed by employing a joint training strategy on all generated FDIA scenarios.