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

Systematic generalisation with group invariant predictions

IA for recognising Traffic Signs using Keras [Tensorflow]

Code for "Universal inference meets random projections: a scalable test for log-concavity"

10th place solution for Google Smartphone Decimeter Challenge at kaggle.

Retrieve and analysis data from SDSS (Sloan Digital Sky Survey)

Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

DGN pymarl - Implementation of DGN on Pymarl, which could be trained by VDN or QMIX

The aim of this project is to build an AI bot that can play the Wordle game, or more generally Squabble

Public scripts, services, and configuration for running a smart home K3S network cluster

E2EDNA2 - An automated pipeline for simulation of DNA aptamers complexed with small molecules and short peptides

Relative Uncertainty Learning for Facial Expression Recognition

Code for ECCV 2020 paper "Contacts and Human Dynamics from Monocular Video".

Source code for our EMNLP'21 paper 《Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning》

PyTorch implementation of the Value Iteration Networks (VIN) (NIPS '16 best paper)

[AAAI2022] Source code for our paper《Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning》

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning (CoRL 2021)

TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition.

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)