Metraipolis › archive › dc_b59138359e13

A Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures — arXiv:2610.33063

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33063
License (as archived)
CC0-1.0
Archived
2026-10-27T07:59:32.064Z
SHA-256 of the archived text
21aef4e16ab5dadeab65cf1179779ec854b7155ef237e5296764c1c066de89ab
Stable URL of this page
https://metraipolis.com/documento/dc_b59138359e13

How to cite

A Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures — arXiv:2610.33063 — arXiv (en), https://arxiv.org/abs/2610.33063 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b59138359e13 (Metraipolis archive dc_b59138359e13, sha256 21aef4e16ab5dadeab65cf1179779ec854b7155ef237e5296764c1c066de89ab)
BibTeX
@misc{dcb59138359e13,
  title = {A Canary in the Neural Mine: Catching an Image Classifier's Silent, Confident Failures — arXiv:2610.33063},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33063},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b59138359e13; sha256 21aef4e16ab5dadeab65cf1179779ec854b7155ef237e5296764c1c066de89ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33063. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deployed vision models auto-accept confident predictions, so high-confidence errors propagate silently. Maximum Softmax Probability (MSP), the standard failure predictor, has a structural blind spot: as a scalar read from the classifier head, it is first-order blind to feature variation orthogonal to its confidence gradient. Through a factorial analysis of feature-space detectors, we identify a conditional-redundancy principle explaining why they fail to complement MSP: the class-separability geometry they measure is already encoded in MSP and collapses under fusion. The signal that survives is class-conditional typicality on the off-manifold residual---and because this residual's distribution varies by backbone, from near-Gaussian to heavy-tailed, it must be estimated non-parametrically. We instantiate these findings as CANARY, a training-free detector that computes a per-class kNN distance on the PCA residual of the penultimate feature, percentile-calibrates it on validation data, and fuses it with MSP through a single validation-tuned weight. CANARY's benefit follows a headroom law: gains grow as baseline MSP quality falls, so a single clean-validation number forecasts the improvement. With every parameter selected on in-distribution data alone, CANARY matches or improves 382 of 385 shift cells (e-AURC; 379 on AUROC) across five backbones, with worst-case regression within seed noise ($-0.0002$ AUROC) and the largest gains on natural distribution shifts (ImageNet-A/R, ObjectNet)---where deployed models are most exposed.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.33063 — 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 2026-10-27T07:55:30.802Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).