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

Author: Wenhao Yu ([email protected]). ACL 2022. Commonsense Reasoning on Knowledge Graph for Text Generation

Repository for the paper "Exploring the Sensory Spaces of English Perceptual Verbs in Natural Language Data"

Lyapunov-guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks

Does MAML Only Work via Feature Re-use? A Data Set Centric Perspective

A simplified framework and utilities for PyTorch

AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert intervention

Using this codebase as a tool for my own research. Making some modifications to the original repo for my own purposes.

Implementation of Diverse Semantic Image Synthesis via Probability Distribution Modeling

A-ESRGAN aims to provide better super-resolution images by using multi-scale attention U-net discriminators.

Optimal Camera Position for a Practical Application of Gaze Estimation on Edge Devices,

A comprehensive list of published machine learning applications to cosmology

Source code for paper: Knowledge Inheritance for Pre-trained Language Models

Deep Unsupervised 3D SfM Face Reconstruction Based on Massive Landmark Bundle Adjustment.

Lama-cleaner: Image inpainting tool powered by LaMa

Detect roadway lanes using Python OpenCV for project during the 5th semester at DHBW Stuttgart for lecture in digital image processing.

Modified fork of Xuebin Qin's U-2-Net Repository. Used for demonstration purposes.

RANZCR-CLiP 7th Place Solution

git《Joint Entity and Relation Extraction with Set Prediction Networks》(2020) GitHub:

This is the code repository for the paper A hierarchical semantic segmentation framework for computer-vision-based bridge column damage detection

Deep Inside Convolutional Networks - This is a caffe implementation to visualize the learnt model