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 reimplementation of the paper Involution: Inverting the Inherence of Convolution for Visual Recognition [CVPR 2021].

Minimal But Practical Image Classifier Pipline Using Pytorch, Finetune on ResNet18, Got 99% Accuracy on Own Small Datasets.

source code of “Visual Saliency Transformer” (ICCV2021)

An 16kHz implementation of HiFi-GAN for soft-vc.

Finite-temperature variational Monte Carlo calculation of uniform electron gas using neural canonical transformation.

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Fast and exact ILP-based solvers for the Minimum Flow Decomposition (MFD) problem, and variants of it.

Leaderboard and Visualization for RLCard

IsoGCN code for ICLR2021

Blender add-on: Add to Cameras menu: View → Camera, View → Add Camera, Camera → View, Previous Camera, Next Camera

Mercer Gaussian Process (MGP) and Fourier Gaussian Process (FGP) Regression

TeST: Temporal-Stable Thresholding for Semi-supervised Learning

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

Data reduction pipeline for KOALA on the AAT.

Binary Stochastic Neurons in PyTorch

A Deep Reinforcement Learning Framework for Stock Market Trading

ExCon: Explanation-driven Supervised Contrastive Learning

Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks

A highly modular PyTorch framework with a focus on Neural Architecture Search (NAS).

A small library of 3D related utilities used in my research.