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

Companion repository to the paper accepted at the 4th ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities

A Number Recognition algorithm

Implementation of Online Label Smoothing in PyTorch

Using pretrained language models for biomedical knowledge graph completion.

Convert ONNX model graph to Keras model format.

Programming with Neural Surrogates of Programs

A simple approach to emable dense segmentation with ViT.

LAnguage Model Analysis

Deep Learning for humans

N-gram models- Unsmoothed, Laplace, Deleted Interpolation

PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"

Learning Time-Critical Responses for Interactive Character Control

🔮 Execution time predictions for deep neural network training iterations across different GPUs.

A PoC Corporation Relationship Knowledge Graph System on top of Nebula Graph.

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

Code for "Adversarial Training for a Hybrid Approach to Aspect-Based Sentiment Analysis

PyTorch Implement for Path Attention Graph Network

Supplementary materials for ISMIR 2021 LBD paper "Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes"

CIFAR-10_train-test - training and testing codes for dataset CIFAR-10

AugLiChem - The augmentation library for chemical systems.