On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective

Kolmogorov-Arnold Networks (KANs) have recently emerged as a novel paradigm for function approximation by leveraging univariate spline-based decompositions inspired by the Kolmogorov–Arnold theorem. Despite their theoretical appeal—particularly the potential for inducing smoother decision boundaries and lower effective Lipschitz constants—their adversarial robustness remains largely unexplored. In this work, we conduct the first comprehensive evaluation of KAN robustness in adversarial settings, focusing on both fully connected (FCKANs) and convolutional (CKANs) instantiations for image classification tasks. Across a wide range of benchmark datasets (MNIST, FashionMNIST, KMNIST, CIFAR-10, SVHN, and a subset of ImageNet), we compare KANs against conventional architectures using an extensive suite of attacks, including white-box methods (FGSM, PGD, C&W, MIM), black-box approaches (Square Attack, SimBA, NES), and ensemble attacks (AutoAttack). Our experiments reveal that while small-and medium-scale KANs are not consistently more robust than their standard counterparts, large-scale KANs exhibit markedly enhanced re-silience against adversarial perturbations. An ablation study further demonstrates that critical hyperparameters—such as number of knots and spline order—significantly influence robustness. Moreover, adversarial training experiments confirm the inherent safety advan-tages of KAN-based architectures. Overall, our findings provide novel insights into the adversarial behavior of KANs and lay a rigorous foundation for future research on robust, interpretable network designs.