Black-box attacks, especially Pixle, reach 99-100% success on Arabic handwriting ConvNet models across two benchmark datasets while preserving character structure.
Leveraging transfer learning and mobile-enabled convolutional neural networks for improved arabic handwritten character recognition,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Lightweight embedded ConvNet ensembles reach accuracy comparable to or better than heavier models for Arabic handwritten character recognition while adding only modest computation.
citing papers explorer
-
Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet models
Black-box attacks, especially Pixle, reach 99-100% success on Arabic handwriting ConvNet models across two benchmark datasets while preserving character structure.
-
Embedded ConvNet Ensembles: A Lightweight Approach to Recognize Arabic Handwritten Characters
Lightweight embedded ConvNet ensembles reach accuracy comparable to or better than heavier models for Arabic handwritten character recognition while adding only modest computation.