[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

Overview

Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

Code for NeurIPS 2021 paper "Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training" by Lue Tao, Lei Feng, Jinfeng Yi, Sheng-Jun Huang, and Songcan Chen.
This repository contains an implementation of the attacks (P1~P5) and the defense (adversarial training) in the paper.

Requirements

Our code relies on PyTorch, which will be automatically installed when you follow the instructions below.

conda create -n delusion python=3.8
conda activate delusion
pip install -r requirements.txt

Running Experiments

  1. Pre-train a standard model on CIFAR-10 (the dataset will be automatically download).
python main.py --train_loss ST
  1. Generate perturbed training data.
python poison.py --poison_type P1
python poison.py --poison_type P2
python poison.py --poison_type P3
python poison.py --poison_type P4
python poison.py --poison_type P5
  1. Visualize the perturbed training data (optional).
tensorboard --logdir ./results
  1. Standard training on the perturbed data.
python main.py --train_loss ST --poison_type P1
python main.py --train_loss ST --poison_type P2
python main.py --train_loss ST --poison_type P3
python main.py --train_loss ST --poison_type P4
python main.py --train_loss ST --poison_type P5
  1. Adversarial training on the perturbed data.
python main.py --train_loss AT --poison_type P1
python main.py --train_loss AT --poison_type P2
python main.py --train_loss AT --poison_type P3
python main.py --train_loss AT --poison_type P4
python main.py --train_loss AT --poison_type P5

Results

Figure 1: An illustration of delusive attacks and adversarial training. Left: Random samples from the CIFAR-10 training set: the original training set D and the perturbed training set DP5 generated using the P5 attack. Right: Natural accuracy evaluated on the CIFAR-10 test set for models trained with: i) standard training on D; ii) adversarial training on D; iii) standard training on DP5; iv) adversarial training on DP5. While standard training on DP5 incurs poor generalization performance on D, adversarial training can help a lot.

 

Table 1: Below we report mean and standard deviation of the test accuracy for the CIFAR-10 dataset. As we can see, the performance deviations of the defense (i.e., adversarial training) are very small (< 0.50%), which hardly effect the results. In contrast, the results of standard training are relatively unstable.

Training method \ Training data P1 P2 P3 P4 P5
Standard training 37.87±0.94 74.24±1.32 15.14±2.10 23.69±2.98 11.76±0.72
Adversarial training 86.59±0.30 89.50±0.21 88.12±0.39 88.15±0.15 88.12±0.43

 

Key takeaways: Our theoretical justifications in the paper, along with the empirical results, suggest that adversarial training is a principled and promising defense against delusive attacks.

Citing this work

@inproceedings{tao2021better,
    title={Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training},
    author={Tao, Lue and Feng, Lei and Yi, Jinfeng and Huang, Sheng-Jun and Chen, Songcan},
    booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
    year={2021}
}
Owner
Lue Tao
Turning Alchemy into Science.
Lue Tao
Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning

Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning Reference Abeßer, J. & Müller, M. Towards Audio Domain Adapt

Jakob Abeßer 2 Jul 06, 2022
FFCV: Fast Forward Computer Vision (and other ML workloads!)

Fast Forward Computer Vision: train models at a fraction of the cost with accele

FFCV 2.3k Jan 03, 2023
OverFeat is a Convolutional Network-based image classifier and feature extractor.

OverFeat OverFeat is a Convolutional Network-based image classifier and feature extractor. OverFeat was trained on the ImageNet dataset and participat

593 Dec 08, 2022
a dnn ai project to classify which food people are eating on audio recordings

Deep Learning - EAT Challenge About This project is part of an AI challenge of the DeepLearning course 2021 at the University of Augsburg. The objecti

Marco Tröster 1 Oct 24, 2021
Code for ICML 2021 paper: How could Neural Networks understand Programs?

OSCAR This repository contains the source code of our ICML 2021 paper How could Neural Networks understand Programs?. Environment Run following comman

Dinglan Peng 115 Dec 17, 2022
Unofficial & improved implementation of NeRF--: Neural Radiance Fields Without Known Camera Parameters

[Unofficial code-base] NeRF--: Neural Radiance Fields Without Known Camera Parameters [ Project | Paper | Official code base ] ⬅️ Thanks the original

Jianfei Guo 239 Dec 22, 2022
Scalable, event-driven, deep-learning-friendly backtesting library

...Minimizing the mean square error on future experience. - Richard S. Sutton BTGym Scalable event-driven RL-friendly backtesting library. Build on

Andrew 922 Dec 27, 2022
Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Language Emergence in Multi Agent Dialog Code for the Paper Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog Satwik Kottur, José M.

Karan Desai 105 Nov 25, 2022
Code for MSc Quantitative Finance Dissertation

MSc Dissertation Code ReadMe Sector Volatility Prediction Performance Using GARCH Models and Artificial Neural Networks Curtis Nybo MSc Quantitative F

2 Dec 01, 2022
This repository contains an implementation of the Permutohedral Attention Module in Pytorch

Permutohedral_attention_module This repository contains an implementation of the Permutohedral Attention Module

Samuel JOUTARD 26 Nov 27, 2022
Prompts - Read a textfile of prompts and import into anki via ankiconnect

prompts read a textfile of prompts and import into anki via ankiconnect Usage In

Alexander Cobleigh 2 Jul 28, 2022
Fast Neural Representations for Direct Volume Rendering

Fast Neural Representations for Direct Volume Rendering Sebastian Weiss, Philipp Hermüller, Rüdiger Westermann This repository contains the code and s

Sebastian Weiss 20 Dec 03, 2022
Implementation for "Manga Filling Style Conversion with Screentone Variational Autoencoder" (SIGGRAPH ASIA 2020 issue)

Manga Filling with ScreenVAE SIGGRAPH ASIA 2020 | Project Website | BibTex This repository is for ScreenVAE introduced in the following paper "Manga F

30 Dec 24, 2022
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

RMNet: Equivalently Removing Residual Connection from Networks This repository is the official implementation of "RMNet: Equivalently Removing Residua

184 Jan 04, 2023
Official code for: A Probabilistic Hard Attention Model For Sequentially Observed Scenes

"A Probabilistic Hard Attention Model For Sequentially Observed Scenes" Authors: Samrudhdhi Rangrej, James Clark Accepted to: BMVC'21 A recurrent atte

5 Nov 19, 2022
验证码识别 深度学习 tensorflow 神经网络

captcha_tf2 验证码识别 深度学习 tensorflow 神经网络 使用卷积神经网络,对字符,数字类型验证码进行识别,tensorflow使用2.0以上 目前项目还在更新中,诸多bug,欢迎提出issue和PR, 希望和你一起共同完善项目。 实例demo 训练过程 优化器选择: Adam

5 Apr 28, 2022
Athena is the only tool that you will ever need to optimize your portfolio.

Athena Portfolio optimization is the process of selecting the best portfolio (asset distribution), out of the set of all portfolios being considered,

Indrajit 1 Mar 25, 2022
PyTorch implementation of U-TAE and PaPs for satellite image time series panoptic segmentation.

Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks (ICCV 2021) This repository is the official implem

71 Jan 04, 2023
[CVPR 2020] Transform and Tell: Entity-Aware News Image Captioning

Transform and Tell: Entity-Aware News Image Captioning This repository contains the code to reproduce the results in our CVPR 2020 paper Transform and

Alasdair Tran 85 Dec 13, 2022
PyTorch ,ONNX and TensorRT implementation of YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4

4.2k Jan 01, 2023