Hierarchical-Bayesian-Defense - Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference (Openreview)

Last update: Dec 02, 2022

Overview

Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference [paper]

Baseline of this code is the official repository for this paper. We just replace the BNN regularizer from ELBO with enhanced Bayesian regularizer based on hierarchical-ELBO.

Citation

If you find this work helpful, please cite it as:

@misc{
lee2021towards,
title={Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference},
author={Byung-Kwan Lee and Youngjoon Yu and Yong Man Ro},
year={2021},
url={https://openreview.net/forum?id=Cue2ZEBf12}
}

Hierarchical-Bayeisan-Defense

Dataset

CIFAR10
STL10
CIFAR100
Tiny-ImageNet

Network

VGG16 (for CIFAR-10/CIFAR-100/Tiny-ImageNet)
Aaron (for STL10)
WideResNet (for CIFAR-10/100)

Attack (by torchattack)

PGD attack
EOT-PGD attack

Defense methods

adv: Adversarial training
adv_vi: Adversarial training with Bayesian neural network
adv_hvi: Adversarial training with Enhanced Bayesian neural network based on hierarchical-ELBO

How to Train

1. Adversarial training

Run train_adv.sh

lr=0.01
steps=10
max_norm=0.03
data=tiny # or `cifar10`, `stl10`, `cifar100`
root=./datasets
model=vgg # vgg for `cifar10` `stl10` `cifar100`, aaron for `stl10`, wide for `cifar10` or `cifar100`
model_out=./checkpoint/${data}_${model}_${max_norm}_adv
echo "Loading: " ${model_out}
CUDA_VISIBLE_DEVICES=0 python ./main_adv.py \
                        --lr ${lr} \
                        --step ${steps} \
                        --max_norm ${max_norm} \
                        --data ${data} \
                        --model ${model} \
                        --root ${root} \
                        --model_out ${model_out}.pth \

2. Adversarial training with BNN

Run train_adv_vi.sh

lr=0.01
steps=10
max_norm=0.03
sigma_0=0.1
init_s=0.1
data=tiny # or `cifar10`, `stl10`, `cifar100`
root=./datasets
model=vgg # vgg for `cifar10` `stl10` `cifar100`, aaron for `stl10`, wide for `cifar10` or `cifar100`
model_out=./checkpoint/${data}_${model}_${max_norm}_adv_vi
echo "Loading: " ${model_out}
CUDA_VISIBLE_DEVICES=0 python3 ./main_adv_vi.py \
                        --lr ${lr} \
                        --step ${steps} \
                        --max_norm ${max_norm} \
                        --sigma_0 ${sigma_0} \
                        --init_s ${init_s} \
                        --data ${data} \
                        --model ${model} \
                        --root ${root} \
                        --model_out ${model_out}.pth \

3. Adversarial training with enhanced Bayesian regularizer based on hierarchical-ELBO

Run train_adv_hvi.sh

lr=0.01
steps=10
max_norm=0.03
sigma_0=0.1
init_s=0.1
data=tiny # or `cifar10`, `stl10`, `cifar100`
root=./datasets
model=vgg # vgg for `cifar10` `stl10` `cifar100`, aaron for `stl10`, wide for `cifar10` or `cifar100`
model_out=./checkpoint/${data}_${model}_${max_norm}_adv_hvi
echo "Loading: " ${model_out}
CUDA_VISIBLE_DEVICES=0 python3 ./main_adv_hvi.py \
                        --lr ${lr} \
                        --step ${steps} \
                        --max_norm ${max_norm} \
                        --sigma_0 ${sigma_0} \
                        --init_s ${init_s} \
                        --data ${data} \
                        --model ${model} \
                        --root ${root} \
                        --model_out ${model_out}.pth \

How to Test

Testing adversarial robustness

Run acc_under_attack.sh

model=vgg # vgg for `cifar10` `stl10` `cifar100`, aaron for `stl10`, wide for `cifar10` or `cifar100`
defense=adv_hvi # or `adv_vi`, `adv`
data=tiny-imagenet # or `cifar10`, `stl10`, `cifar100`
root=./datasets
n_ensemble=50
step=10
max_norm=0.03
echo "Loading" ./checkpoint/${data}_${model}_${max_norm}_${defense}.pth

CUDA_VISIBLE_DEVICES=0 python3 acc_under_attack.py \
    --model $model \
    --defense $defense \
    --data $data \
    --root $root \
    --n_ensemble $n_ensemble \
    --step $step \
    --max_norm $max_norm

How to check the learning parameters and KL divergence

Run check_parameters.sh

model=vgg # vgg for `cifar10` `stl10` `cifar100`, aaron for `stl10`, wide for `cifar10` or `cifar100`
defense=adv_hvi # or `adv_vi`
data=tiny-imagenet # or `cifar10`, `stl10`, `cifar100`
max_norm=0.03
echo "Loading" ./checkpoint/${data}_${model}_${max_norm}_${defense}.pth

CUDA_VISIBLE_DEVICES=0 python3 check_parameters.py \
    --model $model \
    --defense $defense \
    --data $data \
    --max_norm $max_norm \

How to check uncertainty by predictive entropy

Run uncertainty.sh

model=vgg # vgg for `cifar10` `stl10` `cifar100`, aaron for `stl10`, wide for `cifar10` or `cifar100`
defense=adv_hvi # or `adv_vi`
data=tiny-imagenet # or `cifar10`, `stl10`, `cifar100`
root=./datasets
n_ensemble=50
step=10
max_norm=0.03
echo "Loading" ./checkpoint/${data}_${model}_${max_norm}_${defense}.pth

CUDA_VISIBLE_DEVICES=0 python3 uncertainty.py \
    --model $model \
    --defense $defense \
    --data $data \
    --root $root \
    --n_ensemble $n_ensemble \
    --step $step \
    --max_norm $max_norm

Hierarchical-Bayesian-Defense - Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference (Openreview)

Related tags

Overview

Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference [paper]

Citation

Hierarchical-Bayeisan-Defense

Dataset

Network

Attack (by torchattack)

Defense methods

How to Train

1. Adversarial training

2. Adversarial training with BNN

3. Adversarial training with enhanced Bayesian regularizer based on hierarchical-ELBO

How to Test

Testing adversarial robustness

How to check the learning parameters and KL divergence

How to check uncertainty by predictive entropy

Owner

LBK

Vector Neurons: A General Framework for SO(3)-Equivariant Networks

PyTorch implementation(s) of various ResNet models from Twitch streams.

Deep Learning ❤️ OneFlow

PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech

Library for 8-bit optimizers and quantization routines.

Non-Imaging Transient Reconstruction And TEmporal Search (NITRATES)

(JMLR' 19) A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)

Code for reproducing our paper: LMSOC: An Approach for Socially Sensitive Pretraining

A lane detection integrated Real-time Instance Segmentation based on YOLACT (You Only Look At CoefficienTs)

A project to build an AI voice assistant using Python . The Voice assistant interacts with the humans to perform basic tasks.

A generator of point clouds dataset for PyPipes.

Awesome-AI-books - Some awesome AI related books and pdfs for learning and downloading

This is the implementation of our work Deep Extreme Cut (DEXTR), for object segmentation from extreme points.

Code for NeurIPS 2021 paper "Curriculum Offline Imitation Learning"

Implementation for "Conditional entropy minimization principle for learning domain invariant representation features"

Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

Official Implementation for Fast Training of Neural Lumigraph Representations using Meta Learning.

A TensorFlow implementation of the Mnemonic Descent Method.

HashNeRF-pytorch - Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives

TalkingHead-1KH is a talking-head dataset consisting of YouTube videos