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

Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.

TumorInsight is a Brain Tumor Detection and Classification model built using RESNET50 architecture.

[ICCV 2021] Deep Hough Voting for Robust Global Registration

Our CIKM21 Paper "Incorporating Query Reformulating Behavior into Web Search Evaluation"

Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.

TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations

Open-AI's DALL-E for large scale training in mesh-tensorflow.

Semi-supevised Semantic Segmentation with High- and Low-level Consistency

Automatically align face images 🙃→🙂. Can also do windowing and warping.

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

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, and Trevor Darrell. CVPR 2015 and PAMI 2016.

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)

PyTorch implementation of our ICCV2021 paper: StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation

基于Pytorch实现优秀的自然图像分割框架！(包括FCN、U-Net和Deeplab)

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

SciPy fixes and extensions

Fuzzy Overclustering (FOC)

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling

API for RL algorithm design & testing of BCA (Building Control Agent) HVAC on EnergyPlus building energy simulator by wrapping their EMS Python API

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

Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.

TumorInsight is a Brain Tumor Detection and Classification model built using RESNET50 architecture.

[ICCV 2021] Deep Hough Voting for Robust Global Registration

Our CIKM21 Paper "Incorporating Query Reformulating Behavior into Web Search Evaluation"

Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.

TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations

Open-AI's DALL-E for large scale training in mesh-tensorflow.

Semi-supevised Semantic Segmentation with High- and Low-level Consistency

Automatically align face images 🙃→🙂. Can also do windowing and warping.

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

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)

PyTorch implementation of our ICCV2021 paper: StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation

基于Pytorch实现优秀的自然图像分割框架！(包括FCN、U-Net和Deeplab)

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

SciPy fixes and extensions

Fuzzy Overclustering (FOC)

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling

API for RL algorithm design & testing of BCA (Building Control Agent) HVAC on EnergyPlus building energy simulator by wrapping their EMS Python API

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, and Trevor Darrell. CVPR 2015 and PAMI 2016.