FedCampus: Privacy-preserving Data Ecosystem for Smart Campus

Abstract

The purpose of our project is to address the pressing concerns around data privacy while leveraging the potential of intelligent devices and massive data in our increasingly connected world. Traditional data-driven AI technologies often require collecting and centralizing data from local devices to a central data center (cloud), which raises not only communications latency but also significant data privacy concerns, such as data misuse and leakage.

To overcome these challenges, our lab, DKU Edge Intelligence lab have recently developed “FedCampus”, a privacy-preserving data platform designed for the smart DKU ecosystem. Our platform incorporates cutting-edge privacy-preserving technologies, e.g., federated learning (FL) and federated analytics (FA). FedCampus aims to learn and provide statistical and insightful information in DKU community such as heavy-hitters (aka popular words/emoji/music) and healthcare data (sleeping/exercising patterns), yet, without collecting/knowing individual private information.

Objectives of the proposed topic

As we have recently launched our project 1.0 version, students for this project do not need to learn from scratch, instead, they can quickly grasp what we have developed and build new stuff that makes our APP more robust and diverse. Basically, we will maintain and develop out FedCampus in the following four main directions:

1. Further develop our built-in mobile application using Flutter that allows for local data processing from users’ devices.

2. Further implement a backend data platform utilizing Django to effectively manage data from mobile phones. This platform will be responsible for data storage and provide a REST API for seamless communication with mobile phones.

3. Further implement FA/FL algorithms, e.g. implementing state-of-art large language model algorithms within its platform algorithms.

Evaluation criteria for the proposed topic

1. Mobile application developer: Responsible for developing and maintaining Flutter mobile applications, handling data collection, distributed data storage, and data transmission. Candidates with experience in application development, software engineering, and object-oriented design are welcome, though not mandatory, familiarity with desktop/web/mobile applications such as WPF, Qt, Vue.js, React, Android, iOS, and Flutter will be helpful.

2. Database/System developer: Responsible for constructing an edge device platform integrated with a backend database system to efficiently handle transmitted data from devices. Proficiency in Python, solid understanding of database design, and experience working with Linux are essential for this role. Familiarity with at least one popular database, such as MySQL, MariaDB, PostgreSQL, or SQLite, is required. Having experience with web API design and web frameworks like Django, Spring Boot, or Ruby on Rails is a plus.

Prerequisite courses: COMPSCI 301/COMPSCI 310

Recommended course: COMPSCI 311.

3. FL algorithm implementor/researcher: Responsible for implementing FL/FA algorithms. The participant should possess a strong foundation in statistics and machine learning. In particular, familiarity with deep learning, popular neural network architectures, and deep learning algorithms is expected.

Prerequisite courses: STATS 302 or COMPSCI 309.