clip-protocol 2.2.0

Protocol to ensure the privatization of

Empowering learning analytics with state-of-the-art differential privacy. Your data stays meaningful — and safe. 🔒📊

Index

• ✨ Project Description
• 🗂 Repository Structure
• 🚀 Online Execution
• ⚙️ Usage
• 📚 Documentation

Project Description

Learning analytics involves collecting and analyzing data about learners to improve educational outcomes. However, this process raises concerns about the privacy of individual data. To address these concerns, this project implements differential privacy algorithms, which add controlled noise to data, ensuring individual privacy while maintaining the overall utility of the dataset. This approach aligns with recent advancements in safeguarding data privacy in learning analytics.

In this project, we explore a privacy protocol for sketching with privacy considerations. The steps it follow

• Setup
• Mask
• Agregation
• Estimation

Repository Structure

The repository is organized as follows:

Local_Privacy
┣ 📂 src
┣ ┣ 📂 clip_protocol
┃ ┃ ┣ 📂 count mean
┃ ┃ ┣ 📂 hadamard mean
┃ ┃ ┣ 📂 main
┃ ┃ ┃ ┣ setup.py
┃ ┃ ┃ ┣ mask.py
┃ ┃ ┃ ┣ agregate.py
┃ ┃ ┃ ┗ estimation.py
┃ ┗ ┗ 📂 utils
┗ 📂 tests

Online Execution

You can execute the code online using Google Colab. Google Colab sessions are intended for individual users and have limitations such as session timeouts after periods of inactivity and maximum session durations.

For single-user dataset scenarios, click this link to execute the method: Execute in Google Colab (Single-User)

Usage

These methods are included in PyPI as you can view here, and can be installed on your device with:

pip install clip-protocol

Once installed, you can execute the following commands to run the privacy adjustment methods.

Setup

Use the following command:

setup -d <dataset>

• dataset: path to the input dataset (.xlsx) you want to setup for tests

Example:

setup -d /path/to/dataset.xlsx

Mask

Use the following command:

mask -d <dataset> -o <output>

• dataset: Path to the input dataset you want to privatize.
• output: Path to where the privatized dataset will be saved.

The output variable is optional, if it is not needed to save the privatized data you can skip it

Agregation

Use the following command:

agregate

Estimation

Estimates the true frequencies from the aggregated privatized data. This command answers frequency queries based on the collected sketches.

estimate

Clear

Use this command when it is needed to delete all data saved from the previous steps.

clip_clear

Important Notes

• Ensure that the paths provided are correct, and that the necessary permissions are granted for writing to the output location.
• In the mask step, the output will be a new file .csv containing the privatized data.

Documentation

The complete documentation for this project is available online. You can access it at the following link:

• Project Documentation - Local Privacy in Learning Analytics

This documentation includes detailed explanations of the algorithms, methods, and the overall structure of the project.

👩‍💻 Authors

Marta Jones 💻

Anailys Hernandez 💡