pgd-adversarial-attacks | Topic | Ecosyste.ms: Repos

Topic: "pgd-adversarial-attacks"

henry8527/GCE

[ICCV'19] Improving Adversarial Robustness via Guided Complement Entropy

Language: Python - Size: 36.1 KB - Last synced at: over 1 year ago - Pushed at: almost 6 years ago - Stars: 39 - Forks: 2

hammaad2002/ASRAdversarialAttacks

An ASR (Automatic Speech Recognition) adversarial attack repository.

Language: Jupyter Notebook - Size: 10 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 6 - Forks: 1

ahmedgh970/adversarial-training

Adversarially Training of Autoencoders for Unsupervised Anomaly Segmentation

Language: Python - Size: 65.4 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 4 - Forks: 0

deepmancer/adversarial-attacks-robustness

Evaluating CNN robustness against various adversarial attacks, including FGSM and PGD.

Language: Jupyter Notebook - Size: 393 KB - Last synced at: 7 months ago - Pushed at: 9 months ago - Stars: 4 - Forks: 0

In the dynamic landscape of medical artificial intelligence, this study explores the vulnerabilities of the Pathology Language-Image Pretraining (PLIP) model, a Vision Language Foundation model, under targeted attacks like PGD adversarial attack.

Language: Jupyter Notebook - Size: 23.5 MB - Last synced at: 12 months ago - Pushed at: 12 months ago - Stars: 4 - Forks: 0

aminul-huq/WideResNet_MNIST_Adversarial_Training

WideResNet implementation on MNIST dataset. FGSM and PGD adversarial attacks on standard training, PGD adversarial training, and Feature Scattering adversarial training.

Language: Python - Size: 19.5 KB - Last synced at: about 2 years ago - Pushed at: almost 5 years ago - Stars: 3 - Forks: 1

LukasDCode/Adversarial_OOD

Language: Jupyter Notebook - Size: 27.5 MB - Last synced at: about 2 years ago - Pushed at: over 2 years ago - Stars: 2 - Forks: 0

rojinakashefi/Adversarial-Robustness

Learning Adversarial Robustness in Machine Learning both Theory and Practice.

Language: Jupyter Notebook - Size: 10.3 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 1 - Forks: 0

gautamHCSCV/Image-Anonymization-using-Adversarial-Attacks

The Fast Gradient Sign Method (FGSM) combines a white box approach with a misclassification goal. It tricks a neural network model into making wrong predictions. We use this technique to anonymize images.

Language: Jupyter Notebook - Size: 20.4 MB - Last synced at: 12 months ago - Pushed at: 12 months ago - Stars: 0 - Forks: 0