Metraipolis › archive › dc_cb88a2ec1d69

CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation — arXiv:2610.19911

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19911
License (as archived)
CC0-1.0
Archived
2026-10-15T14:19:01.739Z
SHA-256 of the archived text
7ce577663301b89ede7d3644022fbd7c5727011256a34068170b37e50df0ab86
Stable URL of this page
https://metraipolis.com/documento/dc_cb88a2ec1d69

How to cite

CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation — arXiv:2610.19911 — arXiv (en), https://arxiv.org/abs/2610.19911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb88a2ec1d69 (Metraipolis archive dc_cb88a2ec1d69, sha256 7ce577663301b89ede7d3644022fbd7c5727011256a34068170b37e50df0ab86)
BibTeX
@misc{dccb88a2ec1d69,
  title = {CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation — arXiv:2610.19911},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19911},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb88a2ec1d69; sha256 7ce577663301b89ede7d3644022fbd7c5727011256a34068170b37e50df0ab86},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Adversarial robustness distillation typically treats a robust teacher as a fixed knowledge source and transfers robustness to a compact student in a one-way manner. This paradigm terminates teacher-student interaction once the student is distilled, thereby discarding potentially useful feedback from the distilled student. However, exploiting such feedback is nontrivial because indiscriminate weak-to-strong transfer may propagate student errors to the teacher. To address this issue, we propose Cyclic Adversarial Robustness Distillation (CARD), a closed-loop framework that turns the distilled student into a feedback source for refining the robust teacher and subsequently transfers the teacher gains back to the same student. CARD first performs strong-to-weak adversarial distillation and then uses reliability-enhanced student feedback to refine the robust teacher. The refinement combines inverse adversarial student feedback with teacher-student discrepancy maximization, after which the refined teacher is used to continue training the same student under the unchanged base distillation objective. We further establish a sample-level sufficient condition for reliable weak-to-strong feedback transfer and derive a distribution-level upper bound on the refined teacher's risk. Experiments on CIFAR-10, CIFAR-100, and TinyImageNet-10 across multiple teacher-student architectures and base distillation methods show that CARD improves adversarial robustness in most evaluated settings while generally preserving clean accuracy. These results show that the distilled student can provide useful feedback to the teacher, enabling robustness transfer to proceed beyond the conventional one-way teacher-to-student paradigm.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.19911 — 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 2026-10-15T13:53:35.672Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).