Blockchain-Driven Federated Learning for Privacy-Preserving Smart Classrooms
Abstract
The adoption of data driven technologies in education has raised concerns about privacy, transparency and trust in centralized education systems. Artificial intelligence and learning analytics are used to personalized learning, however, their reliance on centralized data systems raises questions about privacy and security of sensitive student data. This research tackles these issues by envisioning a decentralized smart classroom employing federated learning and blockchain technologies. Federated learning allows collaborative model training without exchanging data, thus maintaining privacy, and blockchain provides transparency, immutability, and trust through decentralized verification and governance. The chapter provides a three-layer conceptual framework of decentralized data governance, collaborative intelligence through federated learning and blockchain-based trust. A realization architecture is also offered to put the framework into practice, along with case-based examples and analyses.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.