search

anirudh9784 / Adversarial-Attacks-and-Defences

A defense algorithm which utilizes the combination of an auto- encoder and block-switching architecture. Auto-coder is intended to remove any perturbations found in input images whereas block switching method is used to make it more robust against White-box attack. Attack is planned using FGSM model, and the subsequent counter-attack by the proposed architecture will take place thereby demonstrating the feasibility and security delivered by the algorithm.
18 stars 7 forks source link

Model weights #2

Open Param-Raval opened 2 years ago

Param-Raval commented 2 years ago

Great project! Would it be possible for you to provide the trained model weights?

Thanks!

anirudh9784 commented 2 years ago

For Auto Encoder right?

anirudh9784 commented 2 years ago

It's greater than the Github size limit. You can download it from here. https://drive.google.com/file/d/1hI2Rv24Bgow5nGw_FJuFXyaMpT7xdHhz/view?usp=sharing

Param-Raval commented 2 years ago

Thanks a lot!

Param-Raval commented 2 years ago

Sorry for reopening this but can you tell us the data and parameters (attack type, # epochs, etc.) on which these model weights were trained? And would I be able to reproduce these weights by simply using the architecture from the AutoEncoder() function in your code?

anirudh9784 commented 2 years ago

The attack type is FGSM ( Fast Gradient Sign Method ), I run it for 40 epochs. You can refer python script.