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

codes for "Scheduled Sampling Based on Decoding Steps for Neural Machine Translation" (long paper of EMNLP-2022)

Space robot - (Course Project) Using the space robot to capture the target satellite that is disabled and spinning, then stabilize and fix it up

Inferring Lexicographically-Ordered Rewards from Preferences

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

Unofficial PyTorch implementation of Attention Free Transformer (AFT) layers by Apple Inc.

IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural Network (PINN) systematically.

An Implementation of SiameseRPN with Feature Pyramid Networks

Pytorch Implementation of "Diagonal Attention and Style-based GAN for Content-Style disentanglement in image generation and translation" (ICCV 2021)

Companion code for the paper "An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence" (NeurIPS 2021)

Python3 Implementation of (Subspace Constrained) Mean Shift Algorithm in Euclidean and Directional Product Spaces

(CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

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

Transfer style api - An API to use with Tranfer Style App, where you can use two image and transfer the style

A python implementation of Yolov5 to detect fire or smoke in the wild in Jetson Xavier nx and Jetson nano

ANEA: Automated (Named) Entity Annotation for German Domain-Specific Texts

Crossover Learning for Fast Online Video Instance Segmentation (ICCV 2021)

FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control

Personalized Transfer of User Preferences for Cross-domain Recommendation (PTUPCDR)

adversarial_multi_armed_bandit_variable_plays

Official MegEngine implementation of CREStereo(CVPR 2022 Oral).