Practical texture constraints (pixelation, limited colors, masking) lower adversarial attack success on overhead vehicle detectors, but combining them with small 3D shape deformation approaches unconstrained texture attack performance.
Szegedyet al.[3] introduced AAs to expose vulnerabilities in deep learning models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detection
Practical texture constraints (pixelation, limited colors, masking) lower adversarial attack success on overhead vehicle detectors, but combining them with small 3D shape deformation approaches unconstrained texture attack performance.