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

A study project using the AA-RMVSNet to reconstruct buildings from multiple images

A Python library created to assist programmers with complex mathematical functions

The source codes for TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation.

[NeurIPS 2021] Official implementation of paper "Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization".

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

Code for the paper "Adapting Monolingual Models: Data can be Scarce when Language Similarity is High"

Auditing Black-Box Prediction Models for Data Minimization Compliance

Implementing DeepMind's Fast Reinforcement Learning paper

Watch faces morph into each other with StyleGAN 2, StyleGAN, and DCGAN!

Joint Learning of 3D Shape Retrieval and Deformation, CVPR 2021

Classify music genre from a 10 second sound stream using a Neural Network.

Official code for article "Expression is enough: Improving traﬀic signal control with advanced traﬀic state representation"

App customer segmentation cohort rfm clustering

sequitur is a library that lets you create and train an autoencoder for sequential data in just two lines of code

PyTorch implementation of PSPNet

An implementation for Neural Architecture Search with Random Labels (CVPR 2021 poster) on Pytorch.

BARF: Bundle-Adjusting Neural Radiance Fields 🤮 (ICCV 2021 oral)

BBB streaming without Xorg and Pulseaudio and Chromium and other nonsense (heavily WIP)

Categorizing comments on YouTube into different categories.

Companion repository to the paper accepted at the 4th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities