← Search

Zhihan JIANG

2 accepted papers

2024

Curvature-Invariant Adversarial Attacks for 3D Point Clouds

AAAI 2024technical

Imperceptibility is one of the crucial requirements for adversarial examples. Previous adversarial attacks on 3D point cloud recognition suffer from noticeable outliers, resulting in low imperceptibility. We think that the drawbacks can be alleviated via taking the local curvature of the point cloud…

Cited by 5SourcePDFScholar
2024

Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning

ICLR 2024poster

Federated learning (FL) inevitably confronts the challenge of system heterogeneity in practical scenarios. To enhance the capabilities of most model-homogeneous FL methods in handling system heterogeneity, we propose a training scheme that can extend their capabilities to cope with this challenge. I…