ByungKwanLee/Super-Fast-Adversarial-Training
Official PyTorch Implementation Code for Developing Super Fast Adversarial Training with Distributed Data Parallel, Channel Last Memory Format, Mixed Precision Training + Adversarial Attack, Faster Adversarial Training, and Fast Forward Computer Vision (FFCV).
This project helps machine learning engineers or researchers quickly train deep neural networks that are robust against adversarial attacks. It takes standard image datasets and a chosen network architecture as input, then outputs a more resilient, adversarially trained model. This is for anyone working with computer vision models who needs to ensure their models are secure and perform reliably even when faced with intentionally deceptive data.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher developing computer vision models and need to accelerate the process of making them resistant to adversarial attacks.
Not ideal if you are not working with deep learning models, image data, or if you do not have access to powerful GPU resources.
Stars
33
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ByungKwanLee/Super-Fast-Adversarial-Training"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
namkoong-lab/dro
A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch
neu-autonomy/nfl_veripy
Formal Verification of Neural Feedback Loops (NFLs)
THUDM/grb
Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for...
MinghuiChen43/awesome-trustworthy-deep-learning
A curated list of trustworthy deep learning papers. Daily updating...
ADA-research/VERONA
A lightweight Python package for setting up robustness experiments and to compute robustness...