hfawaz/ijcnn19attacks
Adversarial Attacks on Deep Neural Networks for Time Series Classification
This project helps evaluate how vulnerable your time series classification models are to subtle, crafted attacks. It takes your existing deep neural network model for time series data and generates 'adversarial' versions of typical time series inputs that trick the model into misclassifying them. This is useful for researchers and data scientists working on the robustness and security of machine learning models in time series applications.
No commits in the last 6 months.
Use this if you need to understand the weaknesses of your deep learning models when classifying time series data against carefully designed perturbations.
Not ideal if you are looking to build a time series classification model from scratch or for general time series forecasting.
Stars
80
Forks
28
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jul 02, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hfawaz/ijcnn19attacks"
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
cleverhans-lab/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
DSE-MSU/DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
BorealisAI/advertorch
A Toolbox for Adversarial Robustness Research