Pytorch implementation of "Geometrically Adaptive Dictionary Attack on Face Recognition" (WACV 2022)

Related tags

Deep LearningGADA
Overview

Geometrically Adaptive Dictionary Attack on Face Recognition

This is the Pytorch code of our paper "Geometrically Adaptive Dictionary Attack on Face Recognition" (WACV2022).

Getting started

Dependencies

The code of GADA uses various packages such as Python 3.7, Pytorch 1.6.0, cython=0.29.21, and it is easy to install them by copying the existing environment to the current system to install them easily.

We have saved the conda environment for both Windows and Ubuntu, and you can copy the conda environment to the current system. You can install the conda environment by entering the following command at the conda prompt.

conda env create -f GADA_ubuntu.yml

After setting the environment, you may need to compile the 3D renderer by entering the command.

At the '_3DDFA_V2\Sim3DR' path

python setup.py build_ext --inplace

Since 3D Renderer has already been compiled on Windows and Ubuntu, there may be no problem in running the experiment without executing the above command.

Pretrained face recognition models

You can download the pretrained face recogntion models from face.evoLVe and CurricularFace

After downloading the checkpoint files, place 'backbone_ir50_ms1m_epoch120.pth' into '/checkpoint/ms1m-ir50/' and 'CurricularFace_Backbone.pth' into '/checkpoint/'

Dataset

You can download test image sequences for the LFW and CPLFW datasets from the following links.

LFW test image sequence

CPLFW test image sequence

Place them into the root folder of the project.

Each image sequence has 500 image pairs for dodging and impersonation attack.

These images are curated from the aligned face datasets provided by face.evoLVe.

Usage

You can perform an attack experiment by entering the following command.

python attack.py --model=2 --attack=EAGD --dataset=LFW

The model argument is the index of the target facial recognition model.

1: CurricularFace ResNet-100, 2: ArcFace ResNet-50, 3: FaceNet

The attack argument indicates the attack method.

HSJA, SO, EA, EAD, EAG, EAGD, EAG, EAGDR, EAGDO, SFA, SFAD, SFAG, SFAGD

If --targeted is given as an execution argument, impersonation attack is performed. If no argument is given, dodging attack is performed by default.

The dataset argument sets which test dataset to use and supports LFW and CPLFW.

If you want to enable stateful detection as a defense, pass the --defense=SD argument to the command line.

When an experiment is completed for 500 test images, a 'Dataset_NumImages_targeted_attackname_targetmodel_defense_.pth' file is created in the results folder like 'CPLFW_500_1_EVGD_IR_50_gaussian_.pth'.

Using plotter.py, you can load the above saved file and print various results, such as the l2 norm of perturbation at 1000, 2000, 5000, and 10000 steps, the average number of queries until the l2 norm of perturbation becomes 2 or 4, adversarial examples, etc.

Citation

If you find this work useful, please consider citing our paper :) We provide a BibTeX entry of our paper below:

    @article{byun2021geometrically,
    title={Geometrically Adaptive Dictionary Attack on Face Recognition},
    author={Byun, Junyoung and Go, Hyojun and Kim, Changick},
    journal={arXiv preprint arXiv:2111.04371},
    year={2021}
    }

Acknowledgement

Official implementation of Few-Shot and Continual Learning with Attentive Independent Mechanisms

Few-Shot and Continual Learning with Attentive Independent Mechanisms This repository is the official implementation of Few-Shot and Continual Learnin

Chikan_Huang 25 Dec 08, 2022
Finding all things on-prem Microsoft for password spraying and enumeration.

msprobe About Installing Usage Examples Coming Soon Acknowledgements About Finding all things on-prem Microsoft for password spraying and enumeration.

205 Jan 09, 2023
Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".

Introdunction This is the official implementation of the paper "Query2Label: A Simple Transformer Way to Multi-Label Classification". Abstract This pa

Shilong Liu 274 Dec 28, 2022
ThunderSVM: A Fast SVM Library on GPUs and CPUs

What's new We have recently released ThunderGBM, a fast GBDT and Random Forest library on GPUs. add scikit-learn interface, see here Overview The miss

Xtra Computing Group 1.4k Dec 22, 2022
Code for the AAAI-2022 paper: Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification (AAAI 2022) Prerequisite PyTorch = 1.2.0 P

16 Dec 14, 2022
Label Hallucination for Few-Shot Classification

Label Hallucination for Few-Shot Classification This repo covers the implementation of the following paper: Label Hallucination for Few-Shot Classific

Yiren Jian 13 Nov 13, 2022
Revisting Open World Object Detection

Revisting Open World Object Detection Installation See INSTALL.md. Dataset Our new data division is based on COCO2017. We divide the training set into

58 Dec 23, 2022
Medical image analysis framework merging ANTsPy and deep learning

ANTsPyNet A collection of deep learning architectures and applications ported to the python language and tools for basic medical image processing. Bas

Advanced Normalization Tools Ecosystem 118 Dec 24, 2022
Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation

Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation Official PyTorch implementation for the paper Look

Rishabh Jangir 20 Nov 24, 2022
PyTorch implementation of the Transformer in Post-LN (Post-LayerNorm) and Pre-LN (Pre-LayerNorm).

Transformer-PyTorch A PyTorch implementation of the Transformer from the paper Attention is All You Need in both Post-LN (Post-LayerNorm) and Pre-LN (

Jared Wang 22 Feb 27, 2022
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

DeepSpeed+Megatron trained the world's most powerful language model: MT-530B DeepSpeed is hiring, come join us! DeepSpeed is a deep learning optimizat

Microsoft 8.4k Dec 28, 2022
Hummingbird compiles trained ML models into tensor computation for faster inference.

Hummingbird Introduction Hummingbird is a library for compiling trained traditional ML models into tensor computations. Hummingbird allows users to se

Microsoft 3.1k Dec 30, 2022
Automated image registration. Registrationimation was too much of a mouthful.

alignimation Automated image registration. Registrationimation was too much of a mouthful. This repo contains the code used for my blog post Alignimat

Ethan Rosenthal 9 Oct 13, 2022
Meta Learning Backpropagation And Improving It (VSML)

Meta Learning Backpropagation And Improving It (VSML) This is research code for the NeurIPS 2021 publication Kirsch & Schmidhuber 2021. Many concepts

Louis Kirsch 22 Dec 21, 2022
This repository implements Douzero's interface to IGCA.

douzero-interface-for-ICGA This repository implements Douzero's interface to ICGA. ./douzero: This directory stores Doudizhu AI projects. ./interface:

zhanggenjin 4 Aug 07, 2022
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Super Resolution Examples We run this script under TensorFlow 2.0 and the TensorLayer2.0+. For TensorLayer 1.4 version, please check release. 🚀 🚀 🚀

TensorLayer Community 2.9k Jan 08, 2023
HIVE: Evaluating the Human Interpretability of Visual Explanations

HIVE: Evaluating the Human Interpretability of Visual Explanations Project Page | Paper This repo provides the code for HIVE, a human evaluation frame

Princeton Visual AI Lab 16 Dec 13, 2022
Vision-and-Language Navigation in Continuous Environments using Habitat

Vision-and-Language Navigation in Continuous Environments (VLN-CE) Project Website — VLN-CE Challenge — RxR-Habitat Challenge Official implementations

Jacob Krantz 132 Jan 02, 2023
Pytorch implementation of MalConv

MalConv-Pytorch A Pytorch implementation of MalConv Desciprtion This is the implementation of MalConv proposed in Malware Detection by Eating a Whole

Alexander H. Liu 58 Oct 26, 2022
Official implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Figure 1: Performance of SegFormer-B0 to SegFormer-B5. Project page

NVIDIA Research Projects 1.4k Dec 31, 2022