Resilient Distributed Adaptive Cyber‐Defense Using Blockchain

Autonomous systems, both cyber and physical, operate in highly contested environments in which it must be assumed that adversaries are capable, agile, and informed about state‐of‐the‐art technology. In order to sustain performance in such environments, systems must be able to adapt autonomously through online machine learning ‐ that is, improve their performance quickly, even over the duration of a single engagement. In this chapter, we outline the challenges of adapting in such environments and propose a solution approach that leverages a variety of recent innovations in reinforcement learning, distributed computing, and trusted consensus algorithms such as Blockchain. We argue that multicomponent systems operating in contested environments must leverage their redundancy for learning while also remaining resilient with respect to component failures and compromises. In particular, to enable and accelerate learning, such systems will have to allow some number of components to operate sub‐optimally to achieve the right exploration‐exploitation balance needed for rapid and effective reinforcement learning. At the same time that some number of components are possibly being sacrificed due to sub‐optimal performance, the underlying mission of the system must be maintained. This leads to challenges in distributed trusted computing such as Byzantine agreement problems. We include a discussion of the role of current Blockchain technology in supporting future multiagent adaptive adversarial autonomy with the desired associated resilience.