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

PyTorch implementation of our method for adversarial attacks and defenses in hyperspectral image classification.

unet for image segmentation

Home for cuQuantum Python & NVIDIA cuQuantum SDK C++ samples

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

Stochastic Scene-Aware Motion Prediction

StyleGAN2 Webtoon / Anime Style Toonify

DvD-TD3: Diversity via Determinants for TD3 version

CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability

Mapping Conditional Distributions for Domain Adaptation Under Generalized Target Shift

Tools for computational pathology

RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?

An open-source, low-cost, image-based weed detection device for fallow scenarios.

Meta Learning Backpropagation And Improving It (VSML)

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

SysWhispers Shellcode Loader

RGB-stacking 🛑 🟩 🔷 for robotic manipulation

ICML 21 - Voice2Series: Reprogramming Acoustic Models for Time Series Classification

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

A Simulated Optimal Intrusion Response Game

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning