KOALA(Kaist Open-source Anonymization pLAtform) is a data anonymization platform designed to help organizations protect sensitive information while still allowing them to leverage valuable data. By utilizing the ARX API, KOALA can quickly and easily anonymize structured data.
-
Anonymization
The anonymization in KOALA performes based on privacy models such as k-anonymity, l-diversity, t-closeness, and differential privacy.
-
Feature Analysis
KOALA provides a feature analysis, which gives the statistical information on the anonymized data.
This information can be used as a decent feedback for choosing other privacy models or adjusting parameters.
-
Image anonymization
KOALA provides image blurring, masking, pixelation, and scrambling features for anonymization.
If there is a human face in the image (photo), please check the
Face Recognitionbutton!The anonymization features will operate on human faces only.
-
Image Encryption
KOALA supports its own image encryption feature through passwords.
By clicking the Encrypt Image button and setting a password, it will be encrypted into
Koala Encrypted File (.kenc).kenc can be decrypted within the KOALA program, and other encrypted images cannot be decrypted.
Before you begin, ensure you have met the following requirements:
- Java 19 or higher
- Apache Maven
You can check your Java version by running
java -versionand your Maven version by runningmvn -vin your terminal.
KOALA uses the following libraries, which are automatically managed by Maven:
- OpenCV
- ARX Data Anonymization Tool
Clone the project using Git or download it:
git clone https://github.com/KAIST-CSRC-Privacy/KOALA.git
cd KOALAUse Maven to install dependencies and build the project:
mvn installDownload the Koala DB file and ensure it is located at (executable path)/data/koala.db to use it properly.
To run the program:
java -jar KOALA-0.1.jarContributions to the project are welcome! Use pull requests on Github.