APC is a transferable input purification method that defends 3D point cloud recognition against adversarial attacks by enforcing geometric and semantic consistency using clean-adversarial pairs and hybrid training.
U-CAN: Unsupervised point cloud denoising with consistency-aware noise2noise match- ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
APC is a transferable input purification method that defends 3D point cloud recognition against adversarial attacks by enforcing geometric and semantic consistency using clean-adversarial pairs and hybrid training.