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

Differentiable Simulation of Soft Multi-body Systems

[CVPR 2022] Official PyTorch Implementation for "Reference-based Video Super-Resolution Using Multi-Camera Video Triplets"

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

MPLP: Metapath-Based Label Propagation for Heterogenous Graphs

Segcache: a memory-efficient and scalable in-memory key-value cache for small objects

Generate Contextual Directory Wordlist For Target Org

A library of multi-agent reinforcement learning components and systems

Official code for the paper "Self-Supervised Prototypical Transfer Learning for Few-Shot Classification"

Deep Learning tutorials in jupyter notebooks.

Fast convergence of detr with spatially modulated co-attention

Misc YOLOL scripts for use in the Starbase space sandbox videogame

Liver segmentation using MONAI and pytorch

Here we present the implementation in TensorFlow of our work about liver lesion segmentation accepted in the Machine Learning 4 Health Workshop

CTC segmentation python package

The implementation of the algorithm in the paper "Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data" published in ICML 2020.

PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

Cross-Task Consistency Learning Framework for Multi-Task Learning

SMIS - Semantically Multi-modal Image Synthesis(CVPR 2020)

Yet another video caption

Human annotated noisy labels for CIFAR-10 and CIFAR-100.