Lujie Huang

Lujie Huang

Auto-generated profile, based on publicly available information

Lujie Huang

Guangzhou University, Guangzhou, Guangdong, CHINA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 October 2024
Verified
Book Chapter
Closed access
PDF file
KTKeke Tang
Keke Tang
LHLujie Huang
Lujie Huang
MFMeie Fang
Meie Fang
DLDaizong Liu
Daizong Liu
XWXiaofei Wang
Xiaofei Wang
Zhihong TianZhihong Tian
Zhihong Tian

28 October 2024
Verified
Conference Paper
Open access
KTKeke Tang
Keke Tang
ZWZhensu Wang
Zhensu Wang
MFMeie Fang
Meie Fang
LHLujie Huang
Lujie Huang
LWLe Wang
Le Wang
Zhihong TianZhihong Tian
Zhihong Tian
Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Despite leveraging various geometric constraints, current adversarial attack strategies often suffer from inadequate imperceptibility. Given that adversarial perturbations tend to disrupt the inherent symmetry in objects, we recognize this disruption as the primary cause of the lack of imperceptibility in these attacks. In this paper, we introduce a novel framework, symmetry-aware imperceptible adversarial attacks on 3D point clouds (SymAttack), to address this issue. Our approach starts by identifying part- and patch-level symmetry elements, and grouping points based on semantic and Euclidean distances, respectively. During the adversarial attack iterations, we intentionally adjust the perturbation vectors on symmetric points relative to their symmetry plane. By preserving symmetry within the attack process, SymAttack significantly enhances imperceptibility. Extensive experiments validate the effectiveness of SymAttack in generating imperceptible adversarial point clouds, demonstrating its superiority over the state-of-the-art methods.