Committee Chair

Xie, Mengjun

Committee Member

Qin, Hong; Liang, Yu

Department

Dept. of Computer Science and Engineering

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

UTC's ForensiQ system demonstrates that Knowledge Graph Question Answering (KGQA) systems can handle the scale and complexity of Internet of Things (IoT) forensics. However, using KGQA systems requires a high level of technical expertise, and there are concerns about ForensiQ's inference speed and generalization ability. This thesis aims to enhance KGQA system usability in IoT forensics by extending ForensiQ’s framework to aid investigators, improving ForensiQ's entity detection speed, and testing performance on rephrased questions. Towards this goal, a Django web application was developed to visualize KGQA reasoning, aid KG exploration, and facilitate the creation of custom KGQA datasets. We also replaced ForensiQ's language-model-based entity detector with a name-dictionary-based one, significantly improving the entity detection speed while maintaining accuracy. Tested with rephrased questions, the extended ForensiQ versions outperform the baseline. The experimental results demonstrate the significant improvement of the extended ForensiQ framework on performance and generalization for IoT forensics investigation.

Acknowledgments

My sincerest thanks and gratitude go to my supervisor, Dr. Mengjun Xie. As the heaviness of the dedication section indicates, I have not always been in the best mental state in the past year. Dr. Xie has extended me boundless grace and showed great compassion and empathy while guiding and advising me throughout the work of this thesis. The fact I have managed to produce this thesis in an area of research I did not know much about initially is a testament to his efforts, knowledge, mentorship, patience, and compassion. I can not thank him enough. I also thank Mr. Ruipeng Zhang. This thesis is a continuation of his work, and he has been very generous with his time and help throughout this thesis. Finally, The research in this thesis was supported in part by the UTC InfoSec Center and National Science Foundation (Award #1663105). Beyond this thesis, I would be remiss not to mention how Dr. Daniel Pack and Dr. Zachary Ruble also guided my work in their Unmanned System Laboratory (USL) with kindness and compassion. In addition to being mentors who helped me learn many things about Machine Learning and made me a better researcher, they kept track of the rising tensions in Sudan and constantly asked about the well-being of my family and friends. I will be forever grateful to the two of you. Many people in UTC showed me the same attitude of compassion and going above and beyond to help me with various issues. This includes lecturers and advisors who taught me courses or guided me in different areas, such as my two thesis committee members, Dr. Hong Qin and Dr. Yu Liang, who helped me in many ways, including administration roles, through the years and further honored me by being on this committee. I also owe a debt of gratitude to many of UTC’s staff, who helped me with more issues than I can count. Special thanks to Ms. Christy Waldrep, Ms. Kim Sapp, Ms. Eva Hunter, and Ms. Lora Cook for helping me so much with many things that often went beyond their duty.

Degree

M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.

Date

8-2024

Subject

Digital forensic science; Internet of things

Keyword

KGQA; IoT Forensics; Digital Forensics

Document Type

Masters theses

DCMI Type

Text

Extent

xiii, 51 leaves

Language

English

Rights

http://rightsstatements.org/vocab/InC/1.0/

License

http://creativecommons.org/licenses/by/4.0/

Date Available

8-1-2025

Download

Available for download on Friday, August 01, 2025

Share

COinS