Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learning

Abstract

gories using adversarial patches without changes and for the remaining three classes with a variation of 1%. Additionally, the statistical analysis showed that the predictions' confidence of BP were not significantly different for each pair of clean and perturbed images in every experiment. These results prove BP's robustness against adversarial examples compared to DCNN and handcrafted features methods, whose performance on the art media classification was compromised with the proposed perturbations. We also ratify the competitive score of BP against the state-of-the-art classifiers for the art media categorization problem.