Black-box attacks, especially Pixle, reach 99-100% success on Arabic handwriting ConvNet models across two benchmark datasets while preserving character structure.
A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
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.