cuge1995/Mesh-Attack
our code for paper '3D Adversarial Attacks Beyond Point Cloud ', Information Sciences, 2023
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.
Stars
36
Forks
3
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
Trusted-AI/adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion,...
bethgelab/foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
DSE-MSU/DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
cleverhans-lab/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
BorealisAI/advertorch
A Toolbox for Adversarial Robustness Research