[ICLR2021] Unlearnable Examples: Making Personal Data Unexploitable

Last update: Dec 07, 2022

Related tags

Overview

Unlearnable Examples

Code for ICLR2021 Spotlight Paper "Unlearnable Examples: Making Personal Data Unexploitable " by Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang.

Quick Start

Use the QuickStart.ipynb notebook for a quick start.

In the notebook, you can find the minimal implementation for generating sample-wise unlearnable examples on CIFAR-10. Please remove mlconfig from models/__init__.py if you are only using the notebook and copy-paste the model to the notebook.

Experiments in the paper.

Check scripts folder for *.sh for each corresponding experiments.

Sample-wise noise for unlearnable example on CIFAR-10

Generate noise for unlearnable examples

python3 perturbation.py --config_path             configs/cifar10                \
                        --exp_name                path/to/your/experiment/folder \
                        --version                 resnet18                       \
                        --train_data_type         CIFAR-10                       \
                        --noise_shape             50000 3 32 32                  \
                        --epsilon                 8                              \
                        --num_steps               20                             \
                        --step_size               0.8                            \
                        --attack_type             min-min                        \
                        --perturb_type            samplewise                      \
                        --universal_stop_error    0.01

Train on unlearnable examples and eval on clean test

python3 -u main.py    --version                 resnet18                       \
                      --exp_name                path/to/your/experiment/folder \
                      --config_path             configs/cifar10                \
                      --train_data_type         PoisonCIFAR10                  \
                      --poison_rate             1.0                            \
                      --perturb_type            samplewise                      \
                      --perturb_tensor_filepath path/to/your/experiment/folder/perturbation.pt \
                      --train

Class-wise noise for unlearnable example on CIFAR-10

Generate noise for unlearnable examples

python3 perturbation.py --config_path             configs/cifar10                \
                        --exp_name                path/to/your/experiment/folder \
                        --version                 resnet18                       \
                        --train_data_type         CIFAR-10                       \
                        --noise_shape             10 3 32 32                     \
                        --epsilon                 8                              \
                        --num_steps               1                              \
                        --step_size               0.8                            \
                        --attack_type             min-min                        \
                        --perturb_type            classwise                      \
                        --universal_train_target  'train_subset'                 \
                        --universal_stop_error    0.1                            \
                        --use_subset

Train on unlearnable examples and eval on clean test

python3 -u main.py    --version                 resnet18                       \
                      --exp_name                path/to/your/experiment/folder \
                      --config_path             configs/cifar10                \
                      --train_data_type         PoisonCIFAR10                  \
                      --poison_rate             1.0                            \
                      --perturb_type            classwise                      \
                      --perturb_tensor_filepath path/to/your/experiment/folder/perturbation.pt \
                      --train

Cite Our Work

@inproceedings{huang2021unlearnable,
    title={Unlearnable Examples: Making Personal Data Unexploitable},
    author={Hanxun Huang and Xingjun Ma and Sarah Monazam Erfani and James Bailey and Yisen Wang},
    booktitle={ICLR},
    year={2021}
}

[ICLR2021] Unlearnable Examples: Making Personal Data Unexploitable

Related tags

Overview

Unlearnable Examples

Quick Start

Use the QuickStart.ipynb notebook for a quick start.

Experiments in the paper.

Sample-wise noise for unlearnable example on CIFAR-10

Generate noise for unlearnable examples

Train on unlearnable examples and eval on clean test

Class-wise noise for unlearnable example on CIFAR-10

Generate noise for unlearnable examples

Train on unlearnable examples and eval on clean test

Cite Our Work

Owner

Hanxun Huang

"Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion"(WWW 2021)

Ivy is a templated deep learning framework which maximizes the portability of deep learning codebases.

A small library of 3D related utilities used in my research.

Tesla Light Show xLights Guide With python

naked is a Python tool which allows you to strip a model and only keep what matters for making predictions.

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent

Multiple style transfer via variational autoencoder

🎃 Core identification module of AI powerful point reading system platform.

HuSpaCy: industrial-strength Hungarian natural language processing

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

RGB-D Local Implicit Function for Depth Completion of Transparent Objects

最新版本yolov5+deepsort目标检测和追踪，支持5.0版本可训练自己数据集

ParaGen is a PyTorch deep learning framework for parallel sequence generation

Efficient 3D Backbone Network for Temporal Modeling

Accompanying code for the paper "A Kernel Test for Causal Association via Noise Contrastive Backdoor Adjustment".

On Out-of-distribution Detection with Energy-based Models

Google AI Open Images - Object Detection Track: Open Solution

Implementation of "Large Steps in Inverse Rendering of Geometry"

Official code for our ICCV paper: "From Continuity to Editability: Inverting GANs with Consecutive Images"