Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems
This addresses systemic vulnerability analysis for complex systems like power grids, though it appears incremental as it builds on existing adversarial and agent-based methods.
The paper tackles the problem of analyzing vulnerabilities in large, complex systems by introducing Adversarial Resilience Learning (ARL), a concept that models neural networks as competitive agents to detect unknown attack vectors, with preliminary results demonstrated in simulated power systems.
This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the roles of attackers or defenders that aim at worsening or improving-or keeping, respectively-defined performance indicators of the system. Our concept provides adaptive, repeatable, actor-based testing with a chance of detecting previously unknown attack vectors. We provide the constitutive nomenclature of ARL and, based on it, the description of experimental setups and results of a preliminary implementation of ARL in simulated power systems.