A distributed algorithm for Android malware detection

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: A distributed algorithm for Android malware detection

ارائه دهنده: Provider: Mohammadali Eftekhari

اساتید راهنما: Supervisors: dr Morteza Yousef Sanati

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: dr Muharram Mansoorizadeh- dr vahid nosrati

زمان و تاریخ ارائه: Time and date of presentation: 2024

مکان ارائه: Place of presentation: Faculty of Engineering

چکیده: Abstract: social networking, and diverse business operations, which puts their personal information at risk due to the vulnerabilities of the Android operating system. The rapid development of Android malware has caused many traditional malware detection methods to lose their accuracy. Research indicates that machine learning is an effective method for detecting malware. The swift evolution of malware decreases the accuracy of trained models over time. Additionally, collecting malware-related data from Android devices compromises user privacy. To address this issue, this paper utilizes incremental and federated learning. Recently, federated learning has been introduced for training machine learning models on decentralized devices to preserve privacy. This paper employs a Multi-Layer Perceptron (MLP) within the federated learning framework. Incremental learning is achieved using the stacking method, a type of ensemble learning. The result of this research is a model with an accuracy of 99.52%, which, compared to existing methods, demonstrates a significant improvement in computational time complexity while enhancing learning quality and model accuracy

فایل: ّFile: Download فایل