The Future of Cyber Systems: Human-AI Reinforcement Learning with Adversarial Robustness
Keywords: Adversarial Machine Learning, Human-Computer Teaming, Autonomous Cyber Security Agents
TL;DR: Seveloping autonomous RL cyber agents that can defend real-world networks in tandem with humans will advancing the science of ML robustness and revolutionize the defense of critical infrastructure.
Abstract: Integrating adversarial machine learning (AML) with cyber data representations that support reinforcement learning would unlock human-ai systems with a capacity to dynamically defend against novel attacks, robustly, at machine speed, and with human intelligence.
All machine learning (ML) has an underpinning need for robustness to natural errors and malicious tampering. However, unlike many consumer/commercial models, all ML systems built for cyber will be operating in an inherently adversarial environment with skilled adversaries taking advantage of any flaw. This paper outlines the research challenges, integration points, and programmatic importance
of such a system, while highlighting the social and scientific benefits of pursuing this ambitious program.
Submission Number: 96
Loading