Szczegóły publikacji
Opis bibliograficzny
One-pixel attacks can improve the correctness of prediction / Wiktoria TAJAK, Adam PIÓRKOWSKI, Karolina Nurzyńska // Applied Sciences (Basel) [Dokument elektroniczny]. — Czasopismo elektroniczne ; ISSN 2076-3417 . — 2026 — vol. 16 iss. 14 art. no. 6988, s. 1-22. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 20-22, Abstr. — Publikacja dostępna online od: 2026-07-12
Autorzy (3)
- AGHTajak Wiktoria
- AGHPiórkowski Adam
- Nurzyńska Karolina
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 169325 |
|---|---|
| Data dodania do BaDAP | 2026-09-11 |
| Tekst źródłowy | URL |
| DOI | 10.3390/app16146988 |
| Rok publikacji | 2026 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | Applied Sciences (Basel) |
Abstract
Convolutional neural networks (CNNs) are widely used in medical image classification, yet their robustness to localized perturbations remains limited. This study evaluates one-pixel attacks on VGG16, MobileNetV2, and EfficientNetV2-B0 using brain tumor MRI images resized to 96 × 96 pixels. Each pixel was systematically perturbed across grayscale intensities, and model responses were analyzed in terms of vulnerability, recoverability, and pixel-level sensitivity. The relationship between prediction confidence and influential pixel locations was also examined. Results show that all models remain vulnerable to one-pixel perturbations despite high accuracy. Misclassified samples exhibit more successful attack locations, while correctly classified samples are more robust. Higher-intensity perturbations more often restore correct predictions in misclassified cases. A monotonic relationship is observed between prediction confidence and pixel sensitivity, where lower confidence corresponds to more influential pixels. Recovery points show spatially concentrated patterns. Overall, pixel-level sensitivity is more strongly associated with prediction correctness and local perturbations than with confidence. These findings are consistent across architectures and suggest that one-pixel analysis is useful for assessing CNN robustness in medical imaging.
