English

A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures

Computer Vision and Pattern Recognition 2026-02-10 v1 Artificial Intelligence

Abstract

Convolutional Neural Networks (CNNs) achieve strong image classification performance but lack interpretability and are vulnerable to adversarial attacks. Neuro-fuzzy hybrids such as DCNFIS replace fully connected CNN classifiers with Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to improve interpretability, yet their robustness remains underexplored. This work compares standard CNNs (ConvNet, VGG, ResNet18) with their ANFIS-augmented counterparts on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 under gradient-based (PGD) and gradient-free (Square) attacks. Results show that ANFIS integration does not consistently improve clean accuracy and has architecture-dependent effects on robustness: ResNet18-ANFIS exhibits improved adversarial robustness, while VGG-ANFIS often underperforms its baseline. These findings suggest that neuro-fuzzy augmentation can enhance robustness in specific architectures but is not universally beneficial.

Keywords

Cite

@article{arxiv.2602.07028,
  title  = {A Comparative Study of Adversarial Robustness in CNN and CNN-ANFIS Architectures},
  author = {Kaaustaaub Shankar and Bharadwaj Dogga and Kelly Cohen},
  journal= {arXiv preprint arXiv:2602.07028},
  year   = {2026}
}

Comments

Accepted to NAFIPS 2026