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

Enigma-Plus - Python based Enigma machine simulator with some extra features

Official implementation of the paper Momentum Capsule Networks (MoCapsNet)

Code for the ECCV2020 paper "A Differentiable Recurrent Surface for Asynchronous Event-Based Data"

NNR conformation conditional and global probabilities estimation and analysis in peptides or proteins fragments

Official repo for our 3DV 2021 paper "Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements".

Yolo algorithm for detection + centroid tracker to track vehicles

Demonstration of transfer of knowledge and generalization with distillation

Facial expression detector

LaneAF: Robust Multi-Lane Detection with Affinity Fields

Wind Speed Prediction using LSTMs in PyTorch

FEDn is an open-source, modular and ML-framework agnostic framework for Federated Machine Learning

ComPhy: Compositional Physical Reasoning ofObjects and Events from Videos

Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model

A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

Official repository of IMPROVING DEEP IMAGE MATTING VIA LOCAL SMOOTHNESS ASSUMPTION.

Tzer: TVM Implementation of "Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation (OOPSLA'22)“.

The Python ensemble sampling toolkit for affine-invariant MCMC

[CVPR'2020] DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data

Malware Env for OpenAI Gym

Data from "HateCheck: Functional Tests for Hate Speech Detection Models" (Röttger et al., ACL 2021)