mlsanityData to 14 Oct 2026

Exploring Adversarial Transferability between Kolmogorov-arnold Networks

arXiv 2503.06276 ↗First posted 8 Mar 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Kolmogorov-Arnold Networks (KANs) have emerged as a transformative model paradigm, significantly impacting various fields. However, their adversarial robustness remains less underexplored, especially across different KAN architectures. To explore this critical safety issue, we conduct an analysis and find that due to overfitting to the specific basis functions of KANs, they possess poor adversarial transferability among different KANs. To tackle this challenge, we propose AdvKAN, the first transfer attack method for KANs. AdvKAN integrates two key components: 1) a Breakthrough-Defense Surrogate Model (BDSM), which employs a breakthrough-defense training strategy to mitigate overfitting to the specific structures of KANs. 2) a Global-Local Interaction (GLI) technique, which promotes sufficient interaction between adversarial gradients of hierarchical levels, further smoothing out loss surfaces of KANs. Both of them work together to enhance the strength of transfer attack among different KANs. Extensive experimental results on various KANs and datasets demonstrate the effectiveness of AdvKAN, which possesses notably superior attack capabilities and deeply reveals the vulnerabilities of KANs. Code will be released upon acceptance.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 8 Mar 2025.

Builds on

40 of 54 references.

References · 40

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  6. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  7. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  8. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 244
  9. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 200
  10. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 179
  11. 2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 128
  12. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 122
28 more
  1. 2024KAN 2.0: Kolmogorov-Arnold Networks Meet Sciencecited by 118
  2. 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 87
  3. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  4. 2024Convolutional Kolmogorov-Arnold Networkscited by 77
  5. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  6. 2024KAN or MLP: A Fairer Comparisoncited by 73
  7. 2024Kolmogorov-Arnold Transformercited by 56
  8. 2024GKAN: Graph Kolmogorov-Arnold Networkscited by 53
  9. 2022Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Inputcited by 50
  10. 2021Triangle Attack: A Query-efficient Decision-based Adversarial Attackcited by 48
  11. 2023Boosting Adversarial Transferability by Achieving Flat Local Maximacited by 48
  12. 2024BSRBF-KAN: A combination of B-splines and Radial Basis Functions in Kolmogorov-Arnold Networkscited by 46
  13. 2024Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformationcited by 42
  14. 2022LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinitycited by 39
  15. 2023OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimizationcited by 37
  16. 2020Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspectivecited by 35
  17. 2023Diversifying the High-level Features for better Adversarial Transferabilitycited by 34
  18. 2024Unveiling the Power of Wavelets: A Wavelet-based Kolmogorov-Arnold Network for Hyperspectral Image Classificationcited by 34
  19. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  20. 2022Boosting the Transferability of Adversarial Attacks with Global Momentum Initializationcited by 29
  21. 2023Rethinking the Backward Propagation for Adversarial Transferabilitycited by 27
  22. 2022Investigating Top-k White-Box and Transferable Black-box Attackcited by 26
  23. 2024KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networkscited by 23
  24. 2021Context-Aware Transfer Attacks for Object Detectioncited by 18
  25. 2024Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysiscited by 16
  26. 2024EPi-cKANs: Elasto-Plasticity Informed Kolmogorov-Arnold Networks Using Chebyshev Polynomialscited by 9
  27. 2023GNP Attack: Transferable Adversarial Examples via Gradient Norm Penaltycited by 8
  28. 2024Boosting Adversarial Transferability with Low-Cost Optimization via Maximin Expected Flatnesscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videoscited by 9
  2. 2025An Effective End-to-End Solution for Multimodal Action Recognitioncited by 3
  3. 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Expertscited by 3
  4. 2026Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Modelscited by 0