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

offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

Multiple types of NN model optimization environments. It is possible to directly access the host PC GUI and the camera to verify the operation. Intel iHD GPU (iGPU) support. NVIDIA GPU (dGPU) support.

EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale

Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(2021) paper

A program that uses computer vision to detect hand gestures, used for controlling movie players.

Software & Hardware to do multi color printing with Sharpies

Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Finite difference solution of 2D Poisson equation. Can handle Dirichlet, Neumann and mixed boundary conditions.

List of content farm sites like g.penzai.com.

Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Trains an agent with stochastic policy gradient ascent to solve the Lunar Lander challenge from OpenAI

ANEA: Distant Supervision for Low-Resource Named Entity Recognition

This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

Source codes of CenterTrack++ in 2021 ICME Workshop on Big Surveillance Data Processing and Analysis

Official Code for "Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning"

PyTorch code for our ECCV 2020 paper "Single Image Super-Resolution via a Holistic Attention Network"

Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

Implementation of the state-of-the-art vision transformers with tensorflow

Training a Resilient Q-Network against Observational Interference, Causal Inference Q-Networks

pytorch implementation of trDesign