cnn2d

GUI-based ransomware attack detection using processor and disk I/O telemetry with CNN2D classification, SHAP explainability, adversarial robustness testing, and 10-fold stratified cross-validation.

FFNN, CNN1D, and CNN2D models for solving the inverse neutron scattering problem by predicting honeycomb-lattice exchange parameters from synthetic spin-wave spectra. The pipeline generates spectra, classifies the sign of J1, predicts J2–J8, and evaluates model accuracy, robustness, and noise sensitivity on test and random parameter sets.