cuge1995/awesome-3D-point-cloud-attacks

List of state of the art papers, code, and other resources

31
/ 100
Emerging

This resource compiles leading research papers and code focused on understanding and mitigating security vulnerabilities in 3D point cloud systems. It provides insights into how malicious actors might subtly alter 3D data (like LiDAR scans or 3D models) to trick automated systems, as well as methods to defend against such attacks. Developers and researchers working with autonomous vehicles, robotics, or 3D computer vision will find this useful for building more robust systems.

111 stars. No commits in the last 6 months.

Use this if you are a developer or researcher focused on enhancing the security and robustness of deep learning models that process 3D point cloud data for tasks like object recognition or scene understanding.

Not ideal if you are looking for a ready-to-use software library for general 3D data processing or visualization, as this resource primarily curates academic research and related code for adversarial attacks and defenses.

3D Computer Vision Autonomous Driving Security Robotics Perception Adversarial Machine Learning Deep Learning Robustness
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

111

Forks

14

Language

License

Last pushed

Dec 03, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cuge1995/awesome-3D-point-cloud-attacks"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.