PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

Related tags

Deep LearningABL
Overview

Anti-Backdoor Learning

PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

Python 3.6 Pytorch 1.10 CUDA 10.0 License CC BY-NC

Check the unlearning effect of ABL with 1% isolated backdoor images:

An Example with Pretrained Model

Pretrained backdoored model: gridTrigger WRN-16-1, target label 0, pretrained weights: ./weight/backdoored_model.

Run the following command will show the effect of unlearning:

$ python quick_unlearning_demo.py 

The training logs are shown in below. We can clearly see how effective and efficient of our ABL, with using only 1% (i.e. 500 examples) isolated backdoored images, can successfully decrease the ASR of backdoored WRN-16-1 from 99.98% to near 0% (almost no drop of CA) on CIFAR-10.

Epoch,Test_clean_acc,Test_bad_acc,Test_clean_loss,Test_bad_loss
0,82.77777777777777,99.9888888888889,0.9145596397187975,0.0007119161817762587
Epoch,Test_clean_acc,Test_bad_acc,Test_clean_loss,Test_bad_loss
1,82.97777777777777,47.13333333333333,0.9546798907385932,4.189897534688313
Epoch,Test_clean_acc,Test_bad_acc,Test_clean_loss,Test_bad_loss
2,82.46666666666667,5.766666666666667,1.034722186088562,15.361101960923937
Epoch,Test_clean_acc,Test_bad_acc,Test_clean_loss,Test_bad_loss
3,82.15555555555555,1.5222222222222221,1.0855470676422119,22.175255742390952
Epoch,Test_clean_acc,Test_bad_acc,Test_clean_loss,Test_bad_loss
4,82.0111111111111,0.7111111111111111,1.1183592330084906,26.754894670274524
Epoch,Test_clean_acc,Test_bad_acc,Test_clean_loss,Test_bad_loss
5,81.86666666666666,0.4777777777777778,1.1441074348025853,30.429284422132703

The unlearning model will be saved at the path 'weight/ABL_results/ .tar'

Please carefully read the quick_unlearning_demo.py , then change the default parameters for your experiment.


Prepare Poisoning Data

We have provided a DatasetBD Class in data_loader.py for generating training set of different backdoor attacks.

The use of this code to create a poisoned data is look like this:

from data_loader import *
    if opt.load_fixed_data:
        # load the fixed poisoned data of numpy format, e.g. Dynamic, FC, DFST attacks etc. 
        # Note that the load data type is a pytorch tensor
        poisoned_data = np.load(opt.poisoned_data_path, allow_pickle=True)
        poisoned_data_loader = DataLoader(dataset=poisoned_data,
                                            batch_size=opt.batch_size,
                                            shuffle=True,
                                            )
    else:
        poisoned_data, poisoned_data_loader = get_backdoor_loader(opt)

    test_clean_loader, test_bad_loader = get_test_loader(opt)

However, for the other attacks such as Dynamic, DFTS, FC, etc. It is not easy to contain them into the get_backdoor_loader . So the much elegant way is to create a local fixed poisoning data of these attacks by using the demo code create_poisoned_data.py, and then load this poisoned data by set the opt.loader_fixed_data == True.

We provide a demo of how to create poisoning data of dynamic attack in the create_backdoor_data dictionary.

Please carefully read the create_poisoned_data.py and get_backdoor_loader, then change the parameters for your experiment.

ABL Stage One: Backdoor Isolation

To obtain the 1% isolation data and isolation model, you can easily run command:

$ python backdoor_isolation.py 

After that, you can get a isolation model and then use it to isolate 1% poisoned data of the lowest training loss. The 1% poisoned data will be saved in the path 'isolation_data' and 'weight/isolation_model' respectively.

Please check more details of our experimental settings in section 4 and Appendix A of paper, then change the parameters in config.py for your experiment.

ABL Stage Two: Backdoor Unlearning

With the 1% isolation backdoor set and a isolation model, we can then continue with the later training of unlearning by running the code:

$ python backdoor_unlearning.py 

Note that at this stage, the backdoor has already been learned by the isolation model. In order to further improve clean accuracy of isolation model, we finetuning the model some epochs before backdoor unlearning. If you want directly to see unlearning result, you can select to skip the finetuning of the isolation model by setting argument of opt.finetuning_ascent_model== False .

The final results of unlearning will be saved in the path ABL_results, and logs . Please carefully read the backdoor_unlearning.py and config.py, then change the parameters for your experiment.

Leader-board of training backdoor-free model on Poisoned dataset

  • Note: Here, we create a leader board for anti-backdoor learning that we want to encourage you to submit your results of training a backdoor-free model on a backdoored CIFAR-10 dataset under our defense setting.
  • Defense setting: We assume the backdoor adversary has pre-generated a set of backdoor examples and has successfully injected these examples into the training dataset. We also assume the defender has full control over the training process but has no prior knowledge of the proportion of backdoor examples in the given dataset. The defender’s goal is to train a model on the given dataset (clean or poisoned) that is as good as models trained on purely clean data.
  • We show our ABL results against BadNets in the table bellow as a competition reference, and we welcome you to submit your paper results to complement this table!

Update News: this result is updated in 2021/10/21

# Paper Venue Poisoning data Architecture Attack type ASR (Defense) CA (Defense)
1 ABL NeurIPS 2021 available WRN-16-1 BadNets 3.04 86.11
2
3
4
5
6
7
8

Source of Backdoor Attacks

Attacks

CL: Clean-label backdoor attacks

SIG: A New Backdoor Attack in CNNS by Training Set Corruption Without Label Poisoning

Barni, M., Kallas, K., & Tondi, B. (2019). > A new Backdoor Attack in CNNs by training set corruption without label poisoning. > arXiv preprint arXiv:1902.11237 superimposed sinusoidal backdoor signal with default parameters """ alpha = 0.2 img = np.float32(img) pattern = np.zeros_like(img) m = pattern.shape[1] for i in range(img.shape[0]): for j in range(img.shape[1]): for k in range(img.shape[2]): pattern[i, j] = delta * np.sin(2 * np.pi * j * f / m) img = alpha * np.uint32(img) + (1 - alpha) * pattern img = np.uint8(np.clip(img, 0, 255)) # if debug: # cv2.imshow('planted image', img) # cv2.waitKey() return img ">
## reference code
def plant_sin_trigger(img, delta=20, f=6, debug=False):
    """
    Implement paper:
    > Barni, M., Kallas, K., & Tondi, B. (2019).
    > A new Backdoor Attack in CNNs by training set corruption without label poisoning.
    > arXiv preprint arXiv:1902.11237
    superimposed sinusoidal backdoor signal with default parameters
    """
    alpha = 0.2
    img = np.float32(img)
    pattern = np.zeros_like(img)
    m = pattern.shape[1]
    for i in range(img.shape[0]):
        for j in range(img.shape[1]):
            for k in range(img.shape[2]):
                pattern[i, j] = delta * np.sin(2 * np.pi * j * f / m)

    img = alpha * np.uint32(img) + (1 - alpha) * pattern
    img = np.uint8(np.clip(img, 0, 255))

    #     if debug:
    #         cv2.imshow('planted image', img)
    #         cv2.waitKey()

    return img

Dynamic: Input-aware Dynamic Backdoor Attack

FC: Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

DFST: Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification

LBA: Latent Backdoor Attacks on Deep Neural Networks

CBA: Composite Backdoor Attack for Deep Neural Network by Mixing Existing Benign Features

Feature space attack benchmark

Note: This repository is the official implementation of Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks.

Library

Note: TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

Backdoors 101 — is a PyTorch framework for state-of-the-art backdoor defenses and attacks on deep learning models.

poisoning Feature space attack benchmark A unified benchmark problem for data poisoning attacks

References

If you find this code is useful for your research, please cite our paper

@inproceedings{li2021anti,
  title={Anti-Backdoor Learning: Training Clean Models on Poisoned Data},
  author={Li, Yige and Lyu, Xixiang and Koren, Nodens and Lyu, Lingjuan and Li, Bo and Ma, Xingjun},
  booktitle={NeurIPS},
  year={2021}
}

Contacts

If you have any questions, leave a message below with GitHub.

Owner
Yige-Li
CV&DeepLearning&Security
Yige-Li
This is the code for CVPR 2021 oral paper: Jigsaw Clustering for Unsupervised Visual Representation Learning

JigsawClustering Jigsaw Clustering for Unsupervised Visual Representation Learning Pengguang Chen, Shu Liu, Jiaya Jia Introduction This project provid

DV Lab 73 Sep 18, 2022
Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Improving Transferability of Representations via Augmentation-Aware Self-Supervision Accepted to NeurIPS 2021 TL;DR: Learning augmentation-aware infor

hankook 38 Sep 16, 2022
O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning (CoRL 2021)

O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning Object-object Interaction Affordance Learning. For a given object-object int

Kaichun Mo 26 Nov 04, 2022
A colab notebook for training Stylegan2-ada on colab, transfer learning onto your own dataset.

Stylegan2-Ada-Google-Colab-Starter-Notebook A no thrills colab notebook for training Stylegan2-ada on colab. transfer learning onto your own dataset h

Harnick Khera 66 Dec 16, 2022
Codebase for Time-series Generative Adversarial Networks (TimeGAN)

Codebase for Time-series Generative Adversarial Networks (TimeGAN)

Jinsung Yoon 532 Dec 31, 2022
Welcome to The Eigensolver Quantum School, a quantum computing crash course designed by students for students.

TEQS Welcome to The Eigensolver Quantum School, a crash course designed by students for students. The aim of this program is to take someone who has n

The Eigensolvers 53 May 18, 2022
Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

(ACMMM 2021 Oral) SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment This repository shows two tasks: Face landmark detection and Fac

BoomStar 51 Dec 13, 2022
Image-popularity-score - A novel deep regression method for image scoring.

Image-popularity-score - A novel deep regression method for image scoring.

Shoaib ahmed 1 Dec 26, 2021
This repository contains a pytorch implementation of "HeadNeRF: A Real-time NeRF-based Parametric Head Model (CVPR 2022)".

HeadNeRF: A Real-time NeRF-based Parametric Head Model This repository contains a pytorch implementation of "HeadNeRF: A Real-time NeRF-based Parametr

294 Jan 01, 2023
CS583: Deep Learning

CS583: Deep Learning

Shusen Wang 2.6k Dec 30, 2022
[NAACL & ACL 2021] SapBERT: Self-alignment pretraining for BERT.

SapBERT: Self-alignment pretraining for BERT This repo holds code for the SapBERT model presented in our NAACL 2021 paper: Self-Alignment Pretraining

Cambridge Language Technology Lab 104 Dec 07, 2022
Code for Recurrent Mask Refinement for Few-Shot Medical Image Segmentation (ICCV 2021).

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation Steps Install any missing packages using pip or conda Preprocess each dataset using

XIE LAB @ UCI 39 Dec 08, 2022
A modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (prediction model)

ParallelFold Author: Bozitao Zhong This is a modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (p

Bozitao Zhong 77 Dec 22, 2022
SHIFT15M: multiobjective large-scale fashion dataset with distributional shifts

[arXiv] The main motivation of the SHIFT15M project is to provide a dataset that contains natural dataset shifts collected from a web service IQON, wh

ZOZO, Inc. 138 Nov 24, 2022
Official pytorch implementation of Active Learning for deep object detection via probabilistic modeling (ICCV 2021)

Active Learning for Deep Object Detection via Probabilistic Modeling This repository is the official PyTorch implementation of Active Learning for Dee

NVIDIA Research Projects 130 Jan 06, 2023
Simple API for UCI Machine Learning Dataset Repository (search, download, analyze)

A simple API for working with University of California, Irvine (UCI) Machine Learning (ML) repository Table of Contents Introduction About Page of the

Tirthajyoti Sarkar 223 Dec 05, 2022
Deep Sea Treasure Environment for Multi-Objective Optimization Research

DeepSeaTreasure Environment Installation In order to get started with this environment, you can install it using the following command: python3 -m pip

imec IDLab 6 Nov 14, 2022
Highway networks implemented in PyTorch.

PyTorch Highway Networks Highway networks implemented in PyTorch. Just the MNIST example from PyTorch hacked to work with Highway layers. Todo Make th

Conner Vercellino 56 Dec 14, 2022
PyTorch implementation of UPFlow (unsupervised optical flow learning)

UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning By Kunming Luo, Chuan Wang, Shuaicheng Liu, Haoqiang Fan, Jue Wang, Jian Sun Megvii

kunming luo 87 Dec 20, 2022
Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction

Unsupervised Feature Loss (UFLoss) for High Fidelity Deep learning (DL)-based reconstruction Official github repository for the paper High Fidelity De

28 Dec 16, 2022