Network Defense is Not a Game
This addresses the challenge of scaling AI for autonomous cyberdefense, though it is incremental in proposing a conceptual shift rather than a breakthrough.
The paper tackles the problem of applying AI to network defense by arguing that it cannot be treated as a single fixed game, proposing to define tasks as distributions of environments to enable techniques like reinforcement learning and facilitate benchmark challenges. It introduces the Network Environment Design approach, which inspired the FARLAND framework used at MITRE to develop RL defenders against drifting adversarial tactics.
Research seeks to apply Artificial Intelligence (AI) to scale and extend the capabilities of human operators to defend networks. A fundamental problem that hinders the generalization of successful AI approaches -- i.e., beating humans at playing games -- is that network defense cannot be defined as a single game with a fixed set of rules. Our position is that network defense is better characterized as a collection of games with uncertain and possibly drifting rules. 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. To demonstrate that an approach for autonomous network defense is practical it is important to be able to reason about the boundaries of its applicability. Hence, we need to be able to define network defense tasks that capture sets of adversarial tactics, techniques, and procedures (TTPs); quality of service (QoS) requirements; and TTPs available to defenders. Furthermore, the abstractions to define these tasks must be extensible; must be backed by well-defined semantics that allow us to reason about distributions of environments; and should enable the generation of data and experiences from which an agent can learn. Our approach named Network Environment Design for Autonomous Cyberdefense inspired the architecture of FARLAND, a Framework for Advanced Reinforcement Learning for Autonomous Network Defense, which we use at MITRE to develop RL network defenders that perform blue actions from the MITRE Shield matrix against attackers with TTPs that drift from MITRE ATT&CK TTPs.