LaED: a novel lightweight, edge-aware and explainable deep learning model for privacy-preserving facial attendance tracking in resource-constrained educational environments

Esther Omolara Abiodun, Oludare Isaac Abiodun, Moatsum Alawida, Bayan Abu Shawar, Abid Mehmood · 2026

Read LaED: a novel lightweight, edge-aware and explainable deep learning model for privacy-preserving facial attendance tracking in resource-constrained educational environments by Esther Omolara Abiodun, Oludare Isaac Abiodun, Moatsum Alawida, Bayan Abu Shawar, Abid Mehmood (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13179389.txt.

Description

Abiodun and four co-authors present LaED, a system for taking class attendance by face recognition, in a paper published in two thousand twenty-six. Schools want the speed of automatic attendance, but face systems raise privacy worries and often need costly hardware.

LaED is designed to run on modest devices at the school itself, keeping biometric data local. It blends checks against replay and deepfake tricks, refuses unknown faces instead of guessing, and learns across schools using federated updates with differential privacy, so raw data never leaves the building. The design also aims to treat faces fairly across demographic groups and to keep an audit trail. Tests used several public face datasets to probe spoofing and fairness.

Catalog record

CREATOREsther Omolara Abiodun, Oludare Isaac Abiodun, Moatsum Alawida, Bayan Abu Shawar, Abid Mehmood
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE105 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13179389

Browse the full library · About the Tower of Babel