[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️⚠️

Sungyoon Lee

Last update: Jul 12, 2022

Related tags

Deep Learning robustness smoothness adversarial-machine-learning adversarial-examples adversarial-attacks robustness-verification loss-landscape certified-defense certified-training

Overview

Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples

This repository is the official implementation of "Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples".

This repository is modified from the CROWN-IBP repository (https://github.com/huanzhang12/CROWN-IBP).

(↑) IBP starts with a higher loss but ends with a relatively lower loss, demonstrating smaller loss variations (colored area). Our method uses tight bounds like CROWN-IBP (β=1), while its landscape is as favorable as IBP, achieving the best performance among these four methods.

Requirements

It requires torch version>=1.3.0.

To install requirements:

conda env create -f environment.yml

Training (and Evaluation)

To train and evaluate the model(s) in the paper, run this command:

python train.py --config config/cifar10.json 
python train.py --config config/cifar10.json "training_params:epsilon=0.007843" "training_params:train_epsilon=0.007843" 
python train.py --config config/mnist.json
python train.py --config config/svhn.json


python eval.py --config config/cifar10.json "eval_params:model_paths=cifar_medium_8px"
python eval.py --config config/cifar10.json "eval_params:model_paths=cifar_medium_2px" "eval_params:epsilon=0.007843"
python eval.py --config config/mnist.json "eval_params:model_paths=mnist_large_train04"
python eval.py --config config/svhn.json "eval_params:model_paths=svhn_large_001"

Official implementation of "Open-set Label Noise Can Improve Robustness Against Inherent Label Noise" (NeurIPS 2021)

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise NeurIPS 2021: This repository is the official implementation of ODNL. Require

12 Dec 7, 2022

Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

Welcome to Barlow Barlow is a tool for identifying the failure modes for a given neural network. To achieve this, Barlow first creates a group of imag

33 Dec 5, 2022

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).

Adaptive Segmentation Mask Attack This repository contains the implementation of the Adaptive Segmentation Mask Attack (ASMA), a targeted adversarial

53 Jul 4, 2022

Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras (ICCV 2021)

N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Gra

32 Dec 26, 2022

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️⚠️

Related tags

Overview

Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples

Requirements

Training (and Evaluation)

You might also like...

Official implementation of "Open-set Label Noise Can Improve Robustness Against Inherent Label Noise" (NeurIPS 2021)

Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).

Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras (ICCV 2021)

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

AugMax: Adversarial Composition of Random Augmentations for Robust Training

This is the code of NeurIPS'21 paper "Towards Enabling Meta-Learning from Target Models".

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Owner

Sungyoon Lee

[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

ColossalAI-Examples - Examples of training models with hybrid parallelism using ColossalAI

The source code for Generating Training Data with Language Models: Towards Zero-Shot Language Understanding.

Defending graph neural networks against adversarial attacks (NeurIPS 2020)

[ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models

transfer attack; adversarial examples; black-box attack; unrestricted Adversarial Attacks on ImageNet; CVPR2021 天池黑盒竞赛

Causal-Adversarial-Instruments - PyTorch Implementation for Developing Library of Investigating Adversarial Examples on A Causal View by Instruments

Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

Super-Fast-Adversarial-Training - A PyTorch Implementation code for developing super fast adversarial training