Mirage: Cyber Deception against Autonomous Cyber Attacks

Abstract

As the capabilities of cyber adversaries continue to evolve, now in parallel to the explosion of maturing and publicly-available artificial intelligence (AI) technologies, cyber defenders may reasonably wonder when cyber adversaries will begin to also field these AI technologies. In this regard, one promising (read: scary) area of AI for cyber attack capabilities are search and automated planning. One possible defensive mechanism against future AI-enabled adversaries is that of cyber deception. To that end, in this work we present and evaluate Mi-rage, an experimentation system that allows for the implementation and testing of novel cyber deceptions designed to counter cyber adversaries that use AI search and planning capabilities.