yamamura-k/ACG
PyTorch implementation of Diversified Adversarial Attack based on Conjugate Gradient Method (ICML2022).
This project helps machine learning engineers and researchers assess the robustness of their image classification models against sophisticated adversarial attacks. It takes an image dataset (like ImageNet, CIFAR-10, or CIFAR-100) and a pre-trained image classification model as input. The output is a quantitative measure of the model's vulnerability, specifically the attack success rates of diversified adversarial attacks.
No commits in the last 6 months.
Use this if you need to rigorously evaluate how well your deep learning image classification models withstand advanced, 'black-box' adversarial attacks, and identify potential weaknesses.
Not ideal if you are looking for a tool to defend against adversarial attacks, or for general model interpretability, rather than solely evaluating attack success.
Stars
10
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jun 26, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yamamura-k/ACG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.