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

Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment"

A PyTorch version of You Only Look at One-level Feature object detector

Text to Image Generation with Semantic-Spatial Aware GAN

Benchmarking Pipeline for Prediction of Protein-Protein Interactions

Source code of NeurIPS 2021 Paper ''Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration''

3.8% and 18.3% on CIFAR-10 and CIFAR-100

VID-Fusion: Robust Visual-Inertial-Dynamics Odometry for Accurate External Force Estimation

A lane detection integrated Real-time Instance Segmentation based on YOLACT (You Only Look At CoefficienTs)

Official Implementation for Fast Training of Neural Lumigraph Representations using Meta Learning.

Implementation of the method described in the Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)

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

The code of paper 'Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection'

Code for Robust Contrastive Learning against Noisy Views

Lazy, a tool for running things in idle time

Semi-supervised Implicit Scene Completion from Sparse LiDAR

Semi-Supervised Learning with Ladder Networks in Keras. Get 98% test accuracy on MNIST with just 100 labeled examples !

Code for the TIP 2021 Paper "Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss"

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Avatarify Python - Avatars for Zoom, Skype and other video-conferencing apps.