Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness

Overview

Orthogonalizing Convolutional Layers with the Cayley Transform

This repository contains implementations and source code to reproduce experiments for the ICLR 2021 spotlight paper Orthogonalizing Convolutional Layers with the Cayley Transform by Asher Trockman and Zico Kolter.

Check out our tutorial on FFT-based convolutions and how to orthogonalize them in this Jupyter notebook.

(more information and code coming soon)

Getting Started

You can clone this repo using:

git clone https://github.com/locuslab/orthogonal-convolutions --recursive

where the --recursive is necessary for the submodules.

The most important dependency is PyTorch >= 1.8. If you like, you can set up a new conda environment:

conda create --name orthoconv python=3.6
conda activate orthoconv
conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge
conda install --file requirements.txt

The Orthogonal Convolutional Layer

Our orthogonal convolutional layer can be found in layers.py. The actual layer is the module CayleyConv. It depends on the function cayley, our implementation of the Cayley transform for (semi-)orthogonalization. Additionally, CayleyConv is a subclass of StridedConv, which emulates striding functionality by reshaping the input tensor.

Running Experiments

The script train.py can be used to run most of the experiments from our paper. To try the "flagship" experiment demonstrating better clean accuracy and -norm-bounded deterministic certifiable robustness, run:

python train.py --epochs=200 --conv=CayleyConv --linear=CayleyLinear

To compare with BCOP as in our paper, run:

python train.py --epochs=200 --conv=BCOP --linear=BjorckLinear
You might also like...
Hierarchical-Bayesian-Defense - Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference (Openreview) [ICCV 2021] Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain
[ICCV 2021] Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain

Amplitude-Phase Recombination (ICCV'21) Official PyTorch implementation of "Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neur

TensorFlow, PyTorch and Numpy layers for generating Orthogonal Polynomials

OrthNet TensorFlow, PyTorch and Numpy layers for generating multi-dimensional Orthogonal Polynomials 1. Installation 2. Usage 3. Polynomials 4. Base C

Paddle implementation for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

ProcrustEs-KGE Paddle implementation for Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis 🙈 A more detailed re

 Orthogonal Over-Parameterized Training
Orthogonal Over-Parameterized Training

The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural network is of great importance. We propose a novel orthogonal over-parameterized training (OPT) framework that can provably minimize the hyperspherical energy which characterizes the diversity of neurons on a hypersphere. See our previous work -- MHE for an in-depth introduction.

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation (ICCV 2021)
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation (ICCV 2021)

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation Home | PyTorch BigGAN Discovery | TensorFlow ProGAN Regulariza

CoSMA: Convolutional Semi-Regular Mesh Autoencoder. From Paper
CoSMA: Convolutional Semi-Regular Mesh Autoencoder. From Paper "Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes"

Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes Implementation of CoSMA: Convolutional Semi-Regular Mesh Autoencoder arXiv p

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

PyTorch implementations of Generative Adversarial Networks.
PyTorch implementations of Generative Adversarial Networks.

This repository has gone stale as I unfortunately do not have the time to maintain it anymore. If you would like to continue the development of it as

Comments
  • I cannot reproduce the reported results in the paper

    I cannot reproduce the reported results in the paper

    Hi. Thank you for sharing the excellent work! However, I cannot reproduce the performance of ResNet9 reported in your paper. I used the command from your github page,

    python train.py --epochs=200 --conv=CayleyConv --linear=CayleyLinear --model ResNet9

    the result is:

    image

    I interpreted the above result as a test accuracy is 72.27 %. As I know, the reported result of ResNet9 is 81.70 +- 0.12 I tried various arguments like epochs=100, lr_max=0.001, eps=0.0, but it failed. How can I reproduce the result for ResNet9 in your paper?

    If I'm wrong, please let me know. Thanks, in advance.

    opened by hyoje42 5
Owner
CMU Locus Lab
Zico Kolter's Research Group
CMU Locus Lab
noisy labels; missing labels; semi-supervised learning; entropy; uncertainty; robustness and generalisation.

ProSelfLC: CVPR 2021 ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks For any specific discussion or potential fu

amos_xwang 57 Dec 4, 2022
Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

Certified Robustness to Adversarial Word Substitutions This is the official GitHub repository for the following paper: Certified Robustness to Adversa

Robin Jia 38 Oct 16, 2022
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition, generation, certification, etc.).

null 3.4k Jan 4, 2023
Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

Semi-supervised-learning-for-medical-image-segmentation. Recently, semi-supervised image segmentation has become a hot topic in medical image computin

Healthcare Intelligence Laboratory 1.3k Jan 3, 2023
Consistency Regularization for Adversarial Robustness

Consistency Regularization for Adversarial Robustness Official PyTorch implementation of Consistency Regularization for Adversarial Robustness by Jiho

null 40 Dec 17, 2022
Pytorch implementation for "Adversarial Robustness under Long-Tailed Distribution" (CVPR 2021 Oral)

Adversarial Long-Tail This repository contains the PyTorch implementation of the paper: Adversarial Robustness under Long-Tailed Distribution, CVPR 20

Tong WU 89 Dec 15, 2022
Multitask Learning Strengthens Adversarial Robustness

Multitask Learning Strengthens Adversarial Robustness

Columbia University 15 Jun 10, 2022
Improving adversarial robustness by a coupling rejection strategy

Adversarial Training with Rectified Rejection The code for the paper Adversarial Training with Rectified Rejection. Environment settings and libraries

Tianyu Pang 29 Jan 6, 2023
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness Code for Paper "Imbalanced Gradients: A Subtle Cause of Overestimated Adv

Hanxun Huang 11 Nov 30, 2022
Code repository accompanying the paper "On Adversarial Robustness: A Neural Architecture Search perspective"

On Adversarial Robustness: A Neural Architecture Search perspective Preparation: Clone the repository: https://github.com/tdchaitanya/nas-robustness.g

Chaitanya Devaguptapu 4 Nov 10, 2022