Scalable rapid framework for evaluating network worst robustness with machine learning

Robustness is pivotal for comprehending, designing, optimizing, and rehabilitating networks, with simulation attacks being the prevailing evaluation method. Simulation attacks are often time-consuming or even impractical; however, a more crucial yet persistently overlooked drawback is that any attack strategy merely provides a potential paradigm of disintegration. The key concern is: in the worst-case scenario or facing the most severe attacks, what is the limit of robustness, referred to as “Worst Robustness†, for a given system? Understanding a system’s worst robustness is imperative for grasping its reliability limits, evaluating protective capabilities, and determining associated design and security maintenance costs. To address these challenges, we introduce the concept of Most Destruction Attack (MDA), which is based on the idea of knowledge stacking. MDA is employed to assess the worst robustness of networks, followed by the application of an adapted CNN algorithm to expedite the prediction of worst robustness. We establish the logical validity of MDA and highlight the exceptional performance of the adapted CNN algorithm in predicting the worst robustness across diverse network topologies. This Worst Robustness Evaluation (WRE) framework is scalable, accommodating various attack strategies, whether existing or prospective, and enhancing predictive capabilities with more powerful machine learning algorithms.