Image-Scaling Attacks and Defenses

Overview

Image-Scaling Attacks & Defenses

This repository belongs to our publication:


Erwin Quiring, David Klein, Daniel Arp, Martin Johns and Konrad Rieck. Adversarial Preprocessing: Understanding and Preventing Image-Scaling Attacks in Machine Learning. Proc. of USENIX Security Symposium, 2020.


Background

For an introduction together with current works on this topic, please visit our website.

Principle of image-scaling attacks

In short, image-scaling attacks enable an adversary to manipulate images, such that they change their appearance/content after downscaling. In particular, the attack generates an image A by slightly perturbing the source image S, such that its scaled version D matches a target image T. This process is illustrated in the figure above.

Getting Started

This repository contains the main code for the attacks and defenses. It has a simple API and can be easily used for own projects. The whole project consists of python code (and some cython additions).

Installation

In short, you just need the following steps (assuming you have Anaconda).

Get the repository:

git clone https://github.com/EQuiw/2019-scalingattack
cd 2019-scalingattack/scaleatt

Create a python environment (to keep your system clean):

conda create --name scaling-attack python=3.6
conda activate scaling-attack

Install python packages and compile cython extensions:

pip install -r requirements.txt
python setup.py build_ext --inplace

Check the README in the scaleatt directory for a detailed introduction how to set up the project (in case of problems).

That's it. For instance, to run the tutorial, you can use (assuming you're still in directory scaleatt and use BASH for $(pwd)):

PYTHONPATH=$(pwd) python tutorial/defense1/step1_non_adaptive_attack.py

Tutorial

Jupyter Notebook

For a quick introduction, I recommend you to look at this jupyter notebook.

Main Tutorial

Check the directory scaleatt/tutorial/ for a detailed tutorial how to run the attacks and defenses.

The directory has the same structure as our evaluation. Each subdirectory corresponds to the subsection from our paper:

  • The directory defense1 corresponds to experiments from Section 5.2 and 5.3
  • The directory defense2 corresponds to experiments from Section 5.4 and 5.5
    • Each subdirectory contains some python scripts that describe the API and the respective steps.

My recommendation: Open each file (in the order of the steps), and then use a python console to run the code step by step interactively.

Owner
Erwin Quiring
Erwin Quiring
Bianace Prediction Pytorch Model

Bianace Prediction Pytorch Model Main Results ETHUSDT from 2021-01-01 00:00:00 t

RoyYang 4 Jul 20, 2022
Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer"

SCGAN Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer" Prepare The pre-trained model is avaiable at http

118 Dec 12, 2022
Official Implementation of "LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks"

LUNAR Official Implementation of "LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networks" Adam Goodge, Bryan Hooi, Ng See Kiong and

Adam Goodge 25 Dec 28, 2022
[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

FaPN: Feature-aligned Pyramid Network for Dense Image Prediction [arXiv] [Project Page] @inproceedings{ huang2021fapn, title={{FaPN}: Feature-alig

Shihua Huang 23 Jul 22, 2022
Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection Acknowledgement We implement our model, BtcDet, based on [OpenPcdet 0.3.0]. Insta

Qiangeng Xu 163 Dec 19, 2022
Example how to deploy deep learning model with aiohttp.

aiohttp-demos Demos for aiohttp project. Contents Imagetagger Deep Learning Image Classifier URL shortener Toxic Comments Classifier Moderator Slack B

aio-libs 661 Jan 04, 2023
Pytorch implementation of "Forward Thinking: Building and Training Neural Networks One Layer at a Time"

forward-thinking-pytorch Pytorch implementation of Forward Thinking: Building and Training Neural Networks One Layer at a Time Requirements Python 2.7

Kim Heecheol 65 Oct 06, 2022
Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)

Weakly- and Semi-Supervised Panoptic Segmentation by Qizhu Li*, Anurag Arnab*, Philip H.S. Torr This repository demonstrates the weakly supervised gro

Qizhu Li 159 Dec 20, 2022
Point detection through multi-instance deep heatmap regression for sutures in endoscopy

Suture detection PyTorch This repo contains the reference implementation of suture detection model in PyTorch for the paper Point detection through mu

artificial intelligence in the area of cardiovascular healthcare 3 Jul 16, 2022
Remote sensing change detection using PaddlePaddle

Change Detection Laboratory Developing and benchmarking deep learning-based remo

Lin Manhui 15 Sep 23, 2022
Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

SSL_OSC Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors

zaixizhang 2 May 14, 2022
Generating Anime Images by Implementing Deep Convolutional Generative Adversarial Networks paper

AnimeGAN - Deep Convolutional Generative Adverserial Network PyTorch implementation of DCGAN introduced in the paper: Unsupervised Representation Lear

Rohit Kukreja 23 Jul 21, 2022
An unsupervised learning framework for depth and ego-motion estimation from monocular videos

SfMLearner This codebase implements the system described in the paper: Unsupervised Learning of Depth and Ego-Motion from Video Tinghui Zhou, Matthew

Tinghui Zhou 1.8k Dec 30, 2022
A Python library for Deep Probabilistic Modeling

Abstract DeeProb-kit is a Python library that implements deep probabilistic models such as various kinds of Sum-Product Networks, Normalizing Flows an

DeeProb-org 46 Dec 26, 2022
The Illinois repository for Climatehack (https://climatehack.ai/). We won 1st place!

Climatehack This is the repository for Illinois's Climatehack Team. We earned first place on the leaderboard with a final score of 0.87992. An overvie

Jatin Mathur 20 Jun 09, 2022
Pip-package for trajectory benchmarking from "Be your own Benchmark: No-Reference Trajectory Metric on Registered Point Clouds", ECMR'21

Map Metrics for Trajectory Quality Map metrics toolkit provides a set of metrics to quantitatively evaluate trajectory quality via estimating consiste

Mobile Robotics Lab. at Skoltech 31 Oct 28, 2022
[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery This is the official implementation of our ICCV 2021 paper News There maybe some bugs in

73 Nov 30, 2022
PASSL包含 SimCLR,MoCo,BYOL,CLIP等基于对比学习的图像自监督算法以及 Vision-Transformer,Swin-Transformer,BEiT,CVT,T2T,MLP_Mixer等视觉Transformer算法

PASSL Introduction PASSL is a Paddle based vision library for state-of-the-art Self-Supervised Learning research with PaddlePaddle. PASSL aims to acce

186 Dec 29, 2022
Multi-Stage Spatial-Temporal Convolutional Neural Network (MS-GCN)

Multi-Stage Spatial-Temporal Convolutional Neural Network (MS-GCN) This code implements the skeleton-based action segmentation MS-GCN model from Autom

Benjamin Filtjens 8 Nov 29, 2022
Tackling data scarcity in Speech Translation using zero-shot multilingual Machine Translation techniques

Tackling data scarcity in Speech Translation using zero-shot multilingual Machine Translation techniques This repository is derived from the NMTGMinor

Tu Anh Dinh 1 Sep 07, 2022