FGSM_MNIST

We're trying to make model better which is robust against to adversarial images, especially made by FGSM. Yann LeCun's MNIST datasets are used.

We're inspired by this tutorial.

ACM 2023 ICIIT conference paper

Paper "A Study on the Optimization of the CNNs for Adversarial Attacks" got accepted to ACM 2023 ICIIT conference wrote by Hyeongcheol Park, Jongweon Kim.

Conference proceeding is not now available(still publishing) but you can see the original paper down below.

This browser does not support PDFs. Please download the PDF to view it: Download PDF.

Fine-tune modeling

1. train model with original MNIST datasets (learning rate == 0.001)
   
2. get adversarial images of MNIST from trained model
   
3. fine-tune model with adversarial images. learning rate is 0.0001 (it may be modified)
   
4. validate with validation set 100 epochs each models
   
5. results saved as a plot
   

A function named
generate_image_adversarial(args) is just interpretation of tensorflow code to pytorch code

Results

red line : accuracy of original MNIST imagess of fine-tuned model
blue line : accuracy of adversarial MNIST images of fine-tuned model

1. Result of none VOneNet finetuned
   
   
   

2. Result of VOneNet finetuned
   
   
   

fine-tunning harms None-VOneNet models's prediction of original data.

But VOnetNet models are robust to fine-tunning

Requirements

• python 3.8+
• pytorch 0.4.1+
• numpy
• tqdm

License

MIT License

trained model

Name	Description
1-layer-linear-classifier	really simple model
3-layer-linear-classifier	add two layer to 1-layer simple model
Convnet	simple convolutional model

Report

This browser does not support PDFs. Please download the PDF to view it: Download PDF.

Longer Motivation

1. VOneNet maybe boosts performance. So we're considering how apply this model to VOneNet