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

Framework web SnakeServer.

Studying Python release adoptions by looking at PyPI downloads

RSC-Net: 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos

Dynamic Graph Event Detection

Few-NERD: Not Only a Few-shot NER Dataset

PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT

Generating Fractals on Starknet with Cairo

Official implementation of "Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection" (ICCV Workshops 2021: RSL-CV).

Simple image captioning model - CLIP prefix captioning.

Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

Neural Ensemble Search for Performant and Calibrated Predictions

CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

High-quality implementations of standard and SOTA methods on a variety of tasks.

Compare GAN code.

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

OpenGAN: Open-Set Recognition via Open Data Generation

PerfFuzz: Automatically Generate Pathological Inputs for C/C++ programs

Parasite: a tool allowing you to compress and decompress files, to reduce their size

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

Learnable Motion Coherence for Correspondence Pruning