Code for "Adversarial attack by dropping information." (ICCV 2021)

Last update: Nov 10, 2022

Overview

AdvDrop

Code for "AdvDrop: Adversarial Attack to DNNs by Dropping Information(ICCV 2021)."

Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract objects (visual item with lost information) is still a challenge. In this work, we investigate this issue from an adversarial viewpoint: will the performance of DNNs decrease even for the images only losing a little information? Towards this end, we propose a novel adversarial attack, named AdvDrop, which crafts adversarial examples by dropping existing information of images. Previously, most adversarial attacks add extra disturbing information on clean images explicitly. Opposite to previous works, our proposed work explores the adversarial robustness of DNN models in a novel perspective by dropping imperceptible details to craft adversarial examples.

[Paper link](http://arxiv.org/abs/2108.09034)

Installation

We highly recommend using conda.

conda create -n advdrop_env python=3.7
source activate advdrop_env

After activating the virtual environment, install pytorch, numpy and torchattacks with:

pip install --user [the package name]

Download dataset.

Usage

Quick Start

python infod_sample.py

Parameters can be speicified in infod_sample.py.

An example

Adv Images

Acknowledgments

We refered Michael's code for JPEG (torch version) part.
We referred [Harry's code style] (https://github.com/Harry24k/adversarial-attacks-pytorch)

Code for "Adversarial attack by dropping information." (ICCV 2021)

Related tags

Overview

AdvDrop

Installation

Usage

Quick Start

An example

Adv Images

Acknowledgments

Citation

Owner

Ranjie Duan

Localized representation learning from Vision and Text (LoVT)

Realtime Face Anti Spoofing with Face Detector based on Deep Learning using Tensorflow/Keras and OpenCV

cisip-FIRe - Fast Image Retrieval

🏖 Keras Implementation of Painting outside the box

A Dataset for Direct Quotation Extraction and Attribution in News Articles.

This git repo contains the implementation of my ML project on Heart Disease Prediction

This is the codebase for the ICLR 2021 paper Trajectory Prediction using Equivariant Continuous Convolution

Exploiting Robust Unsupervised Video Person Re-identification

Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

A chemical analysis of lipophilicities & molecule drawings including ML

Pytorch implementation for "Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter".

paper list in the area of reinforcenment learning for recommendation systems

PyTorch implementation of NIPS 2017 paper Dynamic Routing Between Capsules

a generic C++ library for image analysis

StyleGAN2 Webtoon / Anime Style Toonify

Implementation of paper "Self-supervised Learning on Graphs:Deep Insights and New Directions"

Blender Python - Node-based multi-line text and image flowchart

FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

Learning a mapping from images to psychological similarity spaces with neural networks.

Ground truth data for the Optical Character Recognition of Historical Classical Commentaries.