Segments-aware universal adversarial perturbations purification on 3D point cloud classifiers

Introduction3D point cloud classifiers, while powerful for representing real-world objects and environments, are vulnerable to adversarial perturbations, particularly Universal Adversarial Perturbations (UAPs). These UAPs pose significant security threats due to their input-agnostic nature. Current...

पूर्ण विवरण

ग्रंथसूची विवरण

मुख्य लेखकों:	Yang Gao, Xianrui Chang, Haoran Li, Jian Xu
स्वरूप:	Artigo
भाषा:	Inglês
प्रकाशित:	Frontiers Media S.A. 2025-11-01
श्रृंखला:	Frontiers in Computer Science
विषय:	deep learning computer vision 3D point cloud adversarial attack security and privacy defense
ऑनलाइन पहुंच:	https://www.frontiersin.org/articles/10.3389/fcomp.2025.1626359/full
टैग:	टैग जोड़ें कोई टैग नहीं, इस रिकॉर्ड को टैग करने वाले पहले व्यक्ति बनें!