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

LSSY量化交易系统

ACL'2021: LM-BFF: Better Few-shot Fine-tuning of Language Models

Speech-Emotion-Analyzer - The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

Face Recognition & AI Based Smart Attendance Monitoring System.

Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

Ascend your Jupyter Notebook usage

Nsdf: A mesh SDF with just some code we can directly paste into our raymarcher

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

Remote sensing change detection using PaddlePaddle

[ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Python script to download the celebA-HQ dataset from google drive

Code for ACL 2019 Paper: "COMET: Commonsense Transformers for Automatic Knowledge Graph Construction"

Unofficial implementation of "Coordinate Attention for Efficient Mobile Network Design"

Implementation of CVPR 2021 paper "Spatially-invariant Style-codes Controlled Makeup Transfer"

This tool uses Deep Learning to help you draw and write with your hand and webcam.

My implementation of Fully Convolutional Neural Networks in Keras

Code for BMVC2021 paper "Boundary Guided Context Aggregation for Semantic Segmentation"

Python implementation of NARS (Non-Axiomatic-Reasoning-System)

Tracking Progress in Question Answering over Knowledge Graphs

Interpretation of T cell states using reference single-cell atlases