Project Abstract

It is becoming more and more important to protect sensitive data as our dependance on smart phones grows. Passwords and biometrics are two great examples of traditional authentication techniques that have drawbacks and can be problematic for user experience and security. The notion of “Air Signatures,” which uses inbuilt sensors like gyroscopes and accelerometers to authenticate users through mid-air gestures and movements during phone contacts, was proposed as a solution to this problem.This study explores the viability of using deep learning for pattern recognition in an Air Signature Authentication System(ASAS). ASAS uses an Agile Software Development Lifecycle (SDLC) to iteratively improve its features while fusing cutting-edge technology with user-centric design approaches. ASAS seeks to improve mobile security by offering a safe and user-friendly substitute for conventional authentication techniques through extensive research, prototyping, testing, and optimization.

Keywords: Mobile Security, Machine Learning, Authentication

 Conference Details

Session: Poster Session A at Poster Stand 77

Location: Sir Stanley Clarke Auditorium at Tuesday 7th 13:30 – 17:00

Markers: Bertie Muller, Hassan Eshkiki

Course: BSc Computer Science, 3rd Year

Future Plans: I’m looking for work