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

implementation of the paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"

Pytorch code for "State-only Imitation with Transition Dynamics Mismatch" (ICLR 2020)

Pytorch implementation of Compressive Transformers, from Deepmind

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

Soft actor-critic is a deep reinforcement learning framework for training maximum entropy policies in continuous domains.

Source code for the GPT-2 story generation models in the EMNLP 2020 paper "STORIUM: A Dataset and Evaluation Platform for Human-in-the-Loop Story Generation"

Exploring Visual Engagement Signals for Representation Learning

Released code for Objects are Different: Flexible Monocular 3D Object Detection, CVPR21

Face Detection and Alignment using Multi-task Cascaded Convolutional Networks (MTCNN)

Keras code and weights files for popular deep learning models.

Official implementation of UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation

Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

Joint Versus Independent Multiview Hashing for Cross-View Retrieval[J] (IEEE TCYB 2021, PyTorch Code)

Repositório criado para abrigar os notebooks com a listas de exercícios propostos pelo professor Gustavo Guanabara do canal Curso em Vídeo do YouTube durante o Curso de Python 3

3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Normal Face Photos

Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

PaRT: Parallel Learning for Robust and Transparent AI

Semantically Contrastive Learning for Low-light Image Enhancement

code for paper -- "Seamless Satellite-image Synthesis"