Document Type

Student Research Paper

Date

Summer 2022

Academic Department

Computer Science

Faculty Advisor(s)

Dr. Jingwen Wang; Dr. Peilong Li

Abstract

Detecting malicious network traffic in real time has become a crucial requirement at smart communities for elderly care and medical facilities with the prevalence of Internet-of-things (IoT) devices. Existing machine learning based solutions for network traffic malware detection often fail to scale with the exponential increase of IoT devices at the facility and to detect malicious traffic with desirable low latency. In this paper we seek to fill the gap by designing a scalable end-to-end network traffic analyzing system that permits real-time malware detection. By leveraging distributed systems such as Apache Kafka and Apache Spark, the system has demonstrated scalable performance as the number of IoT devices grow. Using Intel’s oneAPI software stack for both machine learning and deep learning models, the model inference speed is boosted by three-fold.

Notes

Scholarship, Creative Arts, and Research Project (SCARP)

Included in

Data Science Commons

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.