Adversarial Robustness in Cognitive Radio Networks

When an adversary gets access to the data sample in the adversarial robustness models and can make data-dependent changes, how has the decision maker consequently, relying deeply upon the adversarially-modified data, to make statistical inference? How can the resilience and elasticity of the network be literally justified from a game theoretical viewpoint $-$ if there exists a tool to measure the aforementioned elasticity? The principle of byzantine resilience distributed hypothesis testing (BRDHT) is considered in this paper for cognitive radio networks (CRNs) $-$ without-loss-of-generality, something that can be extended to any type of homogeneous or heterogeneous networks. We use the temporal rate of the $\alpha-$leakage as the appropriate tool which we measure the aforementioned resilience through. We take into account the main problem from an information theoretic point of view via an exploration over the \textit{adversarial robustness} of distributed hypothesis testing rules. We chiefly examine if one can write $\mathbb{F}=ma$ for the main problem, consequently, we define a nested bi-level $-$ even 3-level including a hidden control-law $-$ mean-field-game (MFG) realisation solving the control dynamics as well. Further discussions are also provided e.g. the synchronisation. Our novel online algorithm $-$ which is named $\mathbb{OBRDHT}$ $-$ and solution are both unique and generic over which an evaluation is finally performed by simulations.