Data

Tools

Indexes

Applications

Experiments

Open Source Science

yolo_adversarial_example_generation

https://github.com/j-reber/yolo_adversarial_example_generation

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: j-reber
  • Language: Python
  • Default Branch: main
  • Size: 1.63 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme Citation

README.md

Adversarial Example Generation for YOLOv8 Models

This repository implements the Dense Adversary Generation Algorithm (Xie et al., ICCV 2017).

Installation

To make the repository work follow these steps. git clone https://github.com/j-reber/yolo_adversarial_example_generation.git python3 -m venv venv \\ source venv/bin/activate pip install -r requirements.txt

Usage

python3 attack_image_non_targeted.py --max_iter 15 --save_perturbation test_data/per.jpg For a list of all available options for the script call: python3 attack_image_non_targeted.py --help

Pull Request and Enhancements

Please note that this repository now only works for YOLOv8 Detection models. Feel free to contribute.

Owner

  • Name: Johannes
  • Login: j-reber
  • Kind: user
  • Company: KIT

CS @KIT

Citation (CITATION.cff) 

cff-version: 1.2.0
message: If you use this software, please cite it using the information below.
title: Adversarial Example Generation for YOLOv8 Models
authors:
  - family-names: Reber
    given-names: Johannes
    affiliation: Karlsruhe Institute of Technology (KIT)
version: 1.0.0
url: https://github.com/j-reber/yolo_adversarial_example_generation
date-released: 2024-08-10

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Dependencies

requirements.txt pypi
  • opencv-python ==4.10.0.84
  • torch ==2.4.0
  • torchvision ==0.19.0
  • tqdm ==4.66.5
  • ultralytics ==8.2.75