Common-attacks-defenses-on-deep-learning-models

Implementation of common attack and defense techniques against ML/DL models. This was done as homeworks for the Trustworthy ML (CS 579) class at Oregon State University
Assignment homepage: https://secure-ai.systems/courses/MLSec/Sp23/homework.html

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
__pycache__		__pycache__
figures		figures
images		images
models		models
reports		reports
.gitignore		.gitignore
README.md		README.md
adv_attack.py		adv_attack.py
adv_train.py		adv_train.py
datasets.py		datasets.py
delete.py		delete.py
dp_train.py		dp_train.py
hw4_train.py		hw4_train.py
mi_attack.py		mi_attack.py
playground.ipynb		playground.ipynb
playground2.ipynb		playground2.ipynb
playground3.ipynb		playground3.ipynb
poison.py		poison.py
poison_craft.py		poison_craft.py
test_accuracy_vs_poison_ratio.png		test_accuracy_vs_poison_ratio.png
train.log		train.log
train.py		train.py
train.sh		train.sh
train_on_server.py		train_on_server.py
valid.py		valid.py

Provide feedback