GTAICRFLMAFeb 5, 2020

Partially Observable Games for Secure Autonomy

arXiv:2002.01969v11 citations
AI Analysis

This work addresses the problem of secure autonomy for autonomous systems and cyber-defense practitioners, but it appears incremental as it combines existing areas into a new framework.

The paper tackles the integration of autonomy and cyber-defense by proposing a two-player partially observable stochastic game framework for mission planning under uncertainty and adversarial decision making, showing that sub-optimal strategies can be synthesized under finite-memory assumptions.

Technology development efforts in autonomy and cyber-defense have been evolving independently of each other, over the past decade. In this paper, we report our ongoing effort to integrate these two presently distinct areas into a single framework. To this end, we propose the two-player partially observable stochastic game formalism to capture both high-level autonomous mission planning under uncertainty and adversarial decision making subject to imperfect information. We show that synthesizing sub-optimal strategies for such games is possible under finite-memory assumptions for both the autonomous decision maker and the cyber-adversary. We then describe an experimental testbed to evaluate the efficacy of the proposed framework.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes