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

League of Legends Reinforcement Learning Environment (LoLRLE) multiple training scenarios using PPO.

Keras udrl - Keras implementation of Upside Down Reinforcement Learning

Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

DI-smartcross - Decision Intelligence Platform for Traffic Crossing Signal Control

[Preprint] ConvMLP: Hierarchical Convolutional MLPs for Vision, 2021

TrTr: Visual Tracking with Transformer

GNN4Traffic - This is the repository for the collection of Graph Neural Network for Traffic Forecasting

FCN (Fully Convolutional Network) is deep fully convolutional neural network architecture for semantic pixel-wise segmentation

Vehicle detection using machine learning and computer vision techniques for Udacity's Self-Driving Car Engineer Nanodegree.

A PyTorch Implementation of Single Shot MultiBox Detector

Official implementation for (Show, Attend and Distill: Knowledge Distillation via Attention-based Feature Matching, AAAI-2021)

Wider-Yolo Kütüphanesi ile Yüz Tespit Uygulamanı Yap

This is a collection of all challenges in HKCERT CTF 2021

Tool cek opsi checkpoint facebook!

simple_pytorch_example project is a toy example of a python script that instantiates and trains a PyTorch neural network on the FashionMNIST dataset

Implementation for the EMNLP 2021 paper "Interactive Machine Comprehension with Dynamic Knowledge Graphs".

Pseudo-Visual Speech Denoising

An easier way to build neural search on the cloud

Adversarial vulnerability of powerful near out-of-distribution detection