[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

SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021)

PyTorch implementation of the TTC algorithm

MediaPipeで姿勢推定を行い、Tokyo2020オリンピック風のピクトグラムを表示するデモ

Process text, including tokenizing and representing sentences as vectors and Applying some concepts like RNN, LSTM and GRU to create a classifier can detect the language in which a sentence is written from among 17 languages.

This is Official implementation for "Pose-guided Feature Disentangling for Occluded Person Re-Identification Based on Transformer" in AAAI2022

(Personalized) Page-Rank computation using PyTorch

Pytorch implementation of the popular Improv RNN model originally proposed by the Magenta team.

Simultaneous NMT/MMT framework in PyTorch

Evaluation Pipeline for our ECCV2020: Journey Towards Tiny Perceptual Super-Resolution.

PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡

Neural Ensemble Search for Performant and Calibrated Predictions

CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution

A simple editor for captions in .SRT file extension

Official code repository for the EMNLP 2021 paper

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

Fusion-DHL: WiFi, IMU, and Floorplan Fusion for Dense History of Locations in Indoor Environments

StarGAN - Official PyTorch Implementation (CVPR 2018)

PyTorch implementation of the paper Deep Networks from the Principle of Rate Reduction

SPEAR: Semi suPErvised dAta progRamming

When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset of 53,000+ Legal Holdings