ylsung/pytorch-adversarial-training

Stars
231
Rank 173,434 (Top 4 %)
Language
Python
Created almost 6 years ago
Updated over 4 years ago

ylsung/pytorch-adversarial-training

ylsung

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

PyTorch-1.0 implementation for the adversarial training on MNIST/CIFAR-10 and visualization on robustness classifier.

Adversarial Training and Visualization

The repo is the PyTorch-1.0 implementation for the adversarial training on MNIST/CIFAR-10. And I also reproduce part of the visualization results in [1].

Note: Not an official implementation.

Adversarial Training

Objective Function
Standard Training	Adversarial Training
$\min \textrm{E}_{(x, y) \in Dataset}[L(x, y; \theta))]$	$\min \textrm{E}_{(x, y) \in Dataset}[\max_{{\left \\| \delta \right \\|}_p < \epsilon} L(x+\delta, y; \theta))]$

where p in the table is usually 2 or inf.

The objective of standard and adversarial training is fundamentally different. In standard training, the classifier minimize the loss computed from the original training data, while in adversarial training, it trains with the worst-case around the original data.

Visualization

In [1], the authors discover that the features learned by the robustness classifier are more human-perceivable. Related results are shown in mnist/cifar-10 folder.

Implementation

Part of the codes in this repo are borrowed/modified from [2], [3], [4] and [5].

References:

[1] D. Tsipras, S. Santurkar, L. Engstrom, A. Turner, A. Madry. Robustness May Be at Odds with Accuracy, https://arxiv.org/abs/1805.12152

[2] https://github.com/MadryLab/mnist_challenge

[3] https://github.com/MadryLab/cifar10_challenge

[4] https://github.com/xternalz/WideResNet-pytorch

[5] https://github.com/utkuozbulak/pytorch-cnn-visualizations

Contact

Yi-Lin Sung, [email protected]

Ladder-Side-Tuning

PyTorch codes for "LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning"

VL_adapter

PyTorch code for "VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks" (CVPR2022)

gnn_few_shot_cifar100

This is the PyTorch-0.4.0 implementation of few-shot learning on CIFAR-100 with graph neural networks (GNN)

vl-merging

PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"

TetrisBattle

Reproduced the popular Facebook game -- Tetris Battle! Also provided openAI environments.

lightning-semi-supervised-learning

Implementation of semi-supervised learning using PyTorch Lightning

ADLxMLDS2017

sparse_update

ECoFLaP

Code for "ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models"

Jupyter Notebook

ylsung.github.io

https://ylsung.github.io/

Taipei_construction_app