Improving adversarial robustness by a coupling rejection strategy

Last update: Jan 06, 2023

Related tags

Deep Learning Rectified-Rejection

Overview

Adversarial Training with Rectified Rejection

The code for the paper Adversarial Training with Rectified Rejection.

Environment settings and libraries we used in our experiments

This project is tested under the following environment settings:

OS: Ubuntu 18.04.4
GPU: Geforce 2080 Ti or Tesla P100
Cuda: 10.1, Cudnn: v7.6
Python: 3.6
PyTorch: >= 1.6.0
Torchvision: >= 0.6.0

Acknowledgement

The codes are modifed based on Rice et al. 2020, and the model architectures are implemented by pytorch-cifar.

Training Commands

Below we provide running commands training the models with the RR module, taking the setting of PGD-AT + RR (ResNet-18) as an example:

python train_cifar.py --model_name PreActResNet18_twobranch_DenseV1 --attack pgd --lr-schedule piecewise \
                                              --epochs 110 --epsilon 8 \
                                              --attack-iters 10 --pgd-alpha 2 \
                                              --fname auto \
                                              --batch-size 128 \
                                              --adaptivetrain --adaptivetrainlambda 1.0 \
                                              --weight_decay 5e-4 \
                                              --twobranch --useBN \
                                              --selfreweightCalibrate \
                                              --dataset 'CIFAR-10' \
                                              --ATframework 'PGDAT' \
                                              --SGconfidenceW

The FLAG --model_name can be PreActResNet18_twobranch_DenseV1 (ResNet-18) or WideResNet_twobranch_DenseV1 (WRN-34-10). For alternating different AT frameworks, we can set the FLAG --ATframework to be one of PGDAT, TRADES, CCAT.

Evaluation Commands

Below we provide running commands for evaluations.

Evaluating under the PGD attacks

The trained model is saved at trained_models/model_path, where the specific name of model_path is automatically generated during training. The command for evaluating under PGD attacks is:

python eval_cifar.py --model_name PreActResNet18_twobranch_DenseV1 --evalset test --norm l_inf --epsilon 8 \
                                              --attack-iters 1000 --pgd-alpha 2 \
                                              --fname trained_models/model_path \
                                              --load_epoch -1 \
                                              --dataset 'CIFAR-10' \
                                              --twobranch --useBN \
                                              --selfreweightCalibrate

Evaluating under the adaptive CW attacks

The parameter FLAGs --binary_search_steps, --CW_iter, --CW_confidence can be changed, where --detectmetric indicates the rejector that needs to be adaptively evaded.

python eval_cifar_CW.py --model_name PreActResNet18_twobranch_DenseV1 --evalset adaptiveCWtest \
                                              --fname trained_models/model_path \
                                              --load_epoch -1 --seed 2020 \
                                              --binary_search_steps 9 --CW_iter 100 --CW_confidence 0 \
                                              --threatmodel linf --reportmodel linf \
                                              --twobranch --useBN \
                                              --selfreweightCalibrate \
                                              --detectmetric 'RR' \
                                              --dataset 'CIFAR-10'

Evaluating under multi-target and GAMA attacks

The running command for evaluating under multi-target attacks is activated by the FLAG --evalonMultitarget as:

python eval_cifar.py --model_name PreActResNet18_twobranch_DenseV1 --evalset test --norm l_inf --epsilon 8 \
                                              --attack-iters 100 --pgd-alpha 2 \
                                              --fname trained_models/model_path \
                                              --load_epoch -1 \
                                              --dataset 'CIFAR-10' \
                                              --twobranch --useBN \
                                              --selfreweightCalibrate \
                                              --evalonMultitarget --restarts 1

The running command for evaluating under GAMA attacks is activated by the FLAG --evalonGAMA_PGD or --evalonGAMA_FW as:

python eval_cifar.py --model_name PreActResNet18_twobranch_DenseV1 --evalset test --norm l_inf --epsilon 8 \
                                              --attack-iters 100 --pgd-alpha 2 \
                                              --fname trained_models/model_path \
                                              --load_epoch -1 \
                                              --dataset 'CIFAR-10' \
                                              --twobranch --useBN \
                                              --selfreweightCalibrate \
                                              --evalonGAMA_FW

Evaluating under CIFAR-10-C

The running command for evaluating on common corruptions in CIFAR-10-C is:

python eval_cifar_CIFAR10-C.py --model_name PreActResNet18_twobranch_DenseV1 \
                                              --fname trained_models/model_path \
                                              --load_epoch -1 \
                                              --dataset 'CIFAR-10' \
                                              --twobranch --useBN \
                                              --selfreweightCalibrate

Improving adversarial robustness by a coupling rejection strategy

Related tags

Overview

Adversarial Training with Rectified Rejection

Environment settings and libraries we used in our experiments

Acknowledgement

Training Commands

Evaluation Commands

Evaluating under the PGD attacks

Evaluating under the adaptive CW attacks

Evaluating under multi-target and GAMA attacks

Evaluating under CIFAR-10-C

Owner

Tianyu Pang

The Turing Change Point Detection Benchmark: An Extensive Benchmark Evaluation of Change Point Detection Algorithms on real-world data

Multiple custom object count and detection using YOLOv3-Tiny method

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs, ICCV 2021

Source code for our paper "Do Not Trust Prediction Scores for Membership Inference Attacks"

SelfAugment extends MoCo to include automatic unsupervised augmentation selection.

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Implementation of momentum^2 teacher

Bayesian optimization in PyTorch

使用yolov5训练自己数据集(详细过程)并通过flask部署

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-local Spatial-Temporal Similarity

Rule Based Classification Project For Python

ObjDetApp deploys a pytorch model for object detection

This repo tries to recognize faces in the dataset you created

Official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch.

Awesome Monocular 3D detection

Migration of Edge-based Distributed Federated Learning

LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

PyTorch code for the paper "FIERY: Future Instance Segmentation in Bird's-Eye view from Surround Monocular Cameras"

ByteTrack超详细教程！训练自己的数据集&&摄像头实时检测跟踪

Implementing a simplified copy of Shazam application from scratch using MinHashing and LSH.

Improving adversarial robustness by a coupling rejection strategy

Related tags

Overview

Adversarial Training with Rectified Rejection

Environment settings and libraries we used in our experiments

Acknowledgement

Training Commands

Evaluation Commands

Evaluating under the PGD attacks

Evaluating under the adaptive CW attacks

Evaluating under multi-target and GAMA attacks

Evaluating under CIFAR-10-C

Owner

Tianyu Pang

The Turing Change Point Detection Benchmark: An Extensive Benchmark Evaluation of Change Point Detection Algorithms on real-world data

Multiple custom object count and detection using YOLOv3-Tiny method

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs, ICCV 2021

Source code for our paper "Do Not Trust Prediction Scores for Membership Inference Attacks"

SelfAugment extends MoCo to include automatic unsupervised augmentation selection.

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Implementation of momentum^2 teacher

Bayesian optimization in PyTorch

使用yolov5训练自己数据集(详细过程)并通过flask部署

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-local Spatial-Temporal Similarity

Rule Based Classification Project For Python

*ObjDetApp* deploys a pytorch model for object detection

This repo tries to recognize faces in the dataset you created

Official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch.

Awesome Monocular 3D detection

Migration of Edge-based Distributed Federated Learning

LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation

PyTorch code for the paper "FIERY: Future Instance Segmentation in Bird's-Eye view from Surround Monocular Cameras"

ByteTrack超详细教程！训练自己的数据集&&摄像头实时检测跟踪

Implementing a simplified copy of Shazam application from scratch using MinHashing and LSH.

ObjDetApp deploys a pytorch model for object detection