Date of Defense

6-11-2024 1:00 PM

Location

E1-1040

Document Type

Thesis Defense

Degree Name

Master of Science in Software Engineering

College

CIT

Department

Computer Science

First Advisor

Dr.Salah Bouktif

Keywords

Android Apps, Permissions, NLP, Machine Learning, Security, BERT, LSTM, Ensemble Models

Abstract

This study develops an NLP-based system to recommend essential permissions for Android apps by analyzing app descriptions. It leverages advanced models, including LSTM and ensemble techniques, to align permissions with app functionality while minimizing unnecessary requests.

Share

COinS
 
Nov 6th, 1:00 PM

PERMISSION RECOMMENDATION FOR ANDROID APPLICATIONS: LEVERAGING NATURAL LANGUAGE PROCESSING ON APP DESCRIPTIONS

E1-1040

This study develops an NLP-based system to recommend essential permissions for Android apps by analyzing app descriptions. It leverages advanced models, including LSTM and ensemble techniques, to align permissions with app functionality while minimizing unnecessary requests.