no code implementations • 29 May 2022 • Andres Molina-Markham, Silvia G. Ionescu, Erin Lanus, Derek Ng, Sam Sommerer, Joseph J. Rushanan
In contrast with established practices that evaluate safety using the same evaluation dataset for all vehicles, we argue that adversarial evaluation fundamentally requires a process that seeks to defeat a specific protection.
no code implementations • 20 Apr 2021 • Andres Molina-Markham, Ransom K. Winder, Ahmad Ridley
Hence, we propose to define network defense tasks as distributions of network environments, to: (i) enable research to apply modern AI techniques, such as unsupervised curriculum learning and reinforcement learning for network defense; and, (ii) facilitate the design of well-defined challenges that can be used to compare approaches for autonomous cyberdefense.