Adaptive Volcano Support Vector Machine (AVSVM) for Efficient Malware Detection

In this paper, we propose the Adaptive Volcano Support Vector Machine (AVSVM)—a novel classification model inspired by the dynamic behavior of volcanic eruptions—for the purpose of enhancing malware detection. Unlike conventional SVMs that rely on static decision boundaries, AVSVM introduces biologically inspired mechanisms such as pressure estimation, eruption-triggered kernel perturbation, lava flow-based margin refinement, and an exponential cooling schedule. These components work synergistically to enable real-time adjustment of the decision surface, allowing the classifier to escape local optima, mitigate class overlap, and stabilize under high-dimensional, noisy, and imbalanced data conditions commonly found in malware detection tasks. Extensive experiments were conducted on the UNSW-NB15 and KDD Cup 1999 datasets, comparing AVSVM to baseline classifiers including traditional SVM, PSO-SVM, and CNN under identical computational settings. On the UNSW-NB15 dataset, AVSVM achieved an accuracy of 96.7%, recall of 95.4%, precision of 96.1%, F1-score of 95.75%, and a false positive rate of only 3.1%, outperforming all benchmarks. Similar improvements were observed on the KDD dataset. In addition, AVSVM demonstrated smooth convergence behavior and statistically significant gains (p < 0.05) across all pairwise comparisons. These results validate the effectiveness of incorporating biologically motivated adaptivity into classical margin-based classifiers and position AVSVM as a promising tool for intelligent malware detection systems.