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

Resources related to EMNLP 2021 paper "FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations"

DL course co-developed by YSDA, HSE and Skoltech

We simulate traveling back in time with a modern camera to rephotograph famous historical subjects.

Episodic-memory - Ego4D Episodic Memory Benchmark

Deep Crop Rotation

A simple Neural Network that predicts the label for a series of handwritten digits

Fuzzing the Kernel Using Unicornafl and AFL++

Code for ICE-BeeM paper - NeurIPS 2020

Code repository for our paper regarding the L3D dataset.

A new benchmark for Icon Question Answering (IconQA) and a large-scale icon dataset Icon645.

CNN visualization tool in TensorFlow

This app is a simple example of using Strealit to create a financial data web app.

PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

Diverse Image Captioning with Context-Object Split Latent Spaces (NeurIPS 2020)

Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

InvTorch: memory-efficient models with invertible functions

MIM: MIM Installs OpenMMLab Packages

Pytorch implementation of Supporting Clustering with Contrastive Learning, NAACL 2021

Image classification for projects and researches