Federated Learning for Secure Sensor Cloud

<p>Intelligent sensing solutions bridge the gap between the physical world and the cyber world by digitizing the sensor data collected from sensor devices. Sensor cloud networks provide resources to physical and virtual sensing devices and enable uninterrupted intelligent solutions to end-users. Thanks to advancements in machine learning algorithms and big data, the automation of mundane tasks with artificial intelligence is becoming a more reliable smart option. However, existing approaches based on centralized Machine Learning (ML) on sensor cloud networks fail to ensure data privacy. Moreover, centralized ML works with the pre-requisite to have the entire training dataset from end-devices transferred to a central server. We propose a Federated Learning (FL) based approach to ensure data privacy on end-devices in a sensor cloud network. Microservices of our approach provides software as a service implementation of FL with instances of cloud servers such as amazon web services (AWS). Our framework enables a personalized version of FL implementation. The framework is built using pure python APIs, which allows simple implementation and helps to skip learning of brand new APIs of an FL framework. Our proposed framework enhances privacy and security with cryptosystem tools to obfuscate the information of the FL process from unauthorized access.</p>

Name thesis:degree_name

Master of Science in Software Engineering

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Software Engineering and Game Design and Development

Year dc:date.available

2021

Author dc:creator

• Mothukuri, Viraaji

Contributors dc:contributor

• Dr. Reza M. Parizi
• Dr. Syedamin Pouriyeh
• Dr. Yan Huang

• Federated Learning
• Decentralized machine learning
• Sensor cloud
• Quantization
• Security
• Cryptosystem.
• Data Science
• Software Engineering

Repository record dc:identifier

https://digitalcommons.kennesaw.edu/msse_etd/5

OAI identifier oai:identifier

oai:digitalcommons.kennesaw.edu:msse_etd-1005