Machine learning solutions with deep multilayer exogenous networks for distributed denial of service attacks model on networked resources in critical infrastructure

The increasing dependency on critical infrastructure and the vulnerability to cyber-attacks, particularly Distributed Denial of Service attacks, pose significant challenges and threats in this cold warfare era. This paper explores an epidemic model based distributed denial of service attacks system to analyze the impact of seclusion strategies on protecting critical infrastructure against cyber-attacks by leveraging machine learning knowledge with non-linear exogenous networks supported with Levenberg-Marquardt backpropagation. The proposed information security model presents the critical infrastructure nodes into susceptible, infected, quarantined and recovered differential compartments for the targeted population to portray the attack's dynamics and quarantine measures effectively. To analyze the rates for infection, efficiency in the quarantine and the recovery state, the synthetic data is acquired to carry out processes on various scenarios with Adams numerical solver and the said information is fed to intelligent supervised nonlinear autoregressive exogenous neural networks to decipher the attack patterns. The efficacy of the proposed stochastic computing paradigm is established on mean squared error-based convergence trends, error in time series illustrations, error-histogram, and error distribution in histograms, statistics on correlation and autocorrelation metrics based on an exhaustive simulation study for an information security model. The validation of the performance of the design nonlinear networks is further endorsed from counterpart's backpropagation schemes of Bayesian regularization and scaled conjugate gradient, based on the results of statistics in terms of mean, standard deviation, worst, and best of the convergence arcs, error distribution on heat map, inference on median with box plots, plot-matrix analysis, violin plots dynamics and computational time analysis, on exhaustive autonomous executions for solving cyber-attack model in information security.