cuge1995/Mesh-Attack

our code for paper '3D Adversarial Attacks Beyond Point Cloud ', Information Sciences, 2023

31
/ 100
Emerging

This project helps evaluate the robustness of 3D object recognition systems against deliberately crafted physical changes. It takes a standard 3D model of an object and generates a slightly altered version, designed to fool AI models even after 3D printing and scanning. Security researchers and AI developers can use this to understand and improve the resilience of 3D vision systems.

No commits in the last 6 months.

Use this if you need to create 3D adversarial examples that maintain their disruptive effect when physically manufactured and scanned, to test the real-world vulnerability of 3D object detection.

Not ideal if you are solely working with digital point cloud data and do not need to consider the physical manifestation or 3D printing of adversarial objects.

3D-vision AI-security adversarial-machine-learning physical-world-AI object-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

36

Forks

3

Language

Python

License

MIT

Last pushed

Mar 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cuge1995/Mesh-Attack"

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