Metraipolis › archive › dc_aabbca82ef37

Adversarial Robustness of Kernel Machines: A Comprehensive Analysis — arXiv:2611.07474

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07474
License (as archived): CC0-1.0
Archived: 2026-11-06T14:42:23.767Z
SHA-256 of the archived text: ccd5fa1863ae6de68caf2bd7dd589030af3c9fdf87fdd08b68372fc85f5b7f8f
Stable URL of this page: https://metraipolis.com/documento/dc_aabbca82ef37

How to cite

Adversarial Robustness of Kernel Machines: A Comprehensive Analysis — arXiv:2611.07474 — arXiv (en), https://arxiv.org/abs/2611.07474 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aabbca82ef37 (Metraipolis archive dc_aabbca82ef37, sha256 ccd5fa1863ae6de68caf2bd7dd589030af3c9fdf87fdd08b68372fc85f5b7f8f)

BibTeX

@misc{dcaabbca82ef37,
  title = {Adversarial Robustness of Kernel Machines: A Comprehensive Analysis — arXiv:2611.07474},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07474},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aabbca82ef37; sha256 ccd5fa1863ae6de68caf2bd7dd589030af3c9fdf87fdd08b68372fc85f5b7f8f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07474. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Kernel machines are an important class of models in machine learning. However, the question of how robust modern kernel machines are to adversarial examples has not been studied comprehensively. In this paper, we provide a thorough empirical investigation of the adversarial robustness of kernel-based models for both binary and multiclass classification tasks, via white-box and black-box evasion attacks. We evaluate the native robustness of kernel machines, random feature classifiers, and the relatively newer Recursive Feature Machines. In addition, we provide an algorithm for approximate adversarial training of kernel machines. Our experiments on classification tasks on image and tabular datasets strongly indicate that kernel machines are natively more robust than neural networks, i.e., their performance degrades more gracefully against adversarial perturbations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.07474 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:18:42.676Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).