mlsanityData to 14 Oct 2026

KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks

arXiv 2608.21488 ↗First posted 21 Aug 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are exposed to adversarial threats. While adversarial attacks fall into various categories, the most prominent category in research studies is evasion. In evasion attacks, the adversary generates perturbed versions of samples, which might not be observable by human eyes. These samples generally fool the machine learning models with high confidence. This phenomenon poses a significant security violation against machine learning models. In this paper, we investigate the certified and empirical robustness of various Kolmogorov-Arnold network architectures against strong evasion attacks. At first, we provide the mathematical foundations for randomized smoothing and interval bound propagation, and report the ℓ2-certified robustness of the models under randomized smoothing. After that, we systematically evaluate the robustness of various defended and undefended KAN models under FGSM, PGD, and C&W attacks in order to find out the optimal defense strategies and architectures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 30 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

21 of 30 references.

References · 21

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  6. 2016Adversarial Machine Learning at Scalecited by 936
  7. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  8. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  9. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 179
  10. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  11. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 125
  12. 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 42
9 more
  1. 2023Understanding Certified Training with Interval Bound Propagationcited by 26
  2. 2024Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysiscited by 16
  3. 2020On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examplescited by 14
  4. 2024KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elementscited by 12
  5. 2024On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspectivecited by 11
  6. 2024A preliminary study on continual learning in computer vision using Kolmogorov-Arnold Networkscited by 7
  7. 2023Certified Adversarial Robustness Within Multiple Perturbation Boundscited by 4
  8. 2025KAN-Mixers: a new deep learning architecture for image classificationcited by 1
  9. 2025Divided We Fall: Defending Against Adversarial Attacks via Soft-Gated Fractional Mixture-of-Experts with Randomized Adversarial Trainingcited by 1

Built on by

Not cited yet.