Mobile User Authentication Via Deep Learning

WINLAB Summer Internship 2021

Group Members: Aditi Satish, Daniel Liu, Sharad Prasad, Emily Gao, David Man

Project Website

Team, Weekly Progress & Presentations, and Code is posted on the website.

​https://sites.google.com/view/mobileuserauthentication

Final Presentation

​https://docs.google.com/presentation/d/1plBITCWYjjxvuRiupZSWg_G6ukwCNL__e8edlOeRl_w/edit?usp=sharing

Project Objective

By using wireless signals as input, we can develop deep learning techniques to extract unique behavioral biometrics to perform user authentication in real-time.

Objectives:

• Use of Wifi signals to capture inherited behavioral characteristics to facilitate identification/authentication.

• Environment Dependent Solution (Robust to Placement).

• To examine CSI of Wifi to study behavioral characteristics.

• Develop a CNN model resilient to spoofing attacks.