AHCI RESEARCH GROUP

Publications

Papers published in international journals,
proceedings of conferences, workshops and books.

OUR RESEARCH

Scientific Publications

How to

Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.

Show all

2025

Chan, S. A. N.; Alalfi, M. H.

SmartTinkerer: Bridging Smart Home Testing Gaps with LLM, Digital Twin & Reinforcement Learning Proceedings Article

In: Shahriar, H.; Alam, K. S.; Ohsaki, H.; Cimato, S.; Capretz, M.; Ahmed, S.; Ahamed, S. I.; Majumder, A. J. A.; Haque, M.; Yoshihisa, T.; Cuzzocrea, A.; Takemoto, M.; Sakib, N.; Elsayed, M. (Ed.): pp. 1452–1461, Institute of Electrical and Electronics Engineers Inc., 2025, ISBN: 9798331574345 (ISBN).

Abstract | Links | BibTeX | Tags: Artificial intelligence, Computer simulation languages, Digital devices, Digital Twins, Home testing, Intelligent buildings, Internet of thing, Internet of Things, Internet of things (IoT), Language Model, Large language model, large language model (LLM), Network Security, Reinforcement Learning, Reinforcement learnings, Security vulnerabilities, Smart homes, Software technology, Software Testing, Software testings, Testing environment, Virtual Reality

@inproceedings{chan_smarttinkerer_2025,

title = {SmartTinkerer: Bridging Smart Home Testing Gaps with LLM, Digital Twin & Reinforcement Learning},

author = {S. A. N. Chan and M. H. Alalfi},

editor = {H. Shahriar and K. S. Alam and H. Ohsaki and S. Cimato and M. Capretz and S. Ahmed and S. I. Ahamed and A. J. A. Majumder and M. Haque and T. Yoshihisa and A. Cuzzocrea and M. Takemoto and N. Sakib and M. Elsayed},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105016150578&doi=10.1109%2FCOMPSAC65507.2025.00182&partnerID=40&md5=39cf3cc230b62795552f38e6ed1222a6},

doi = {10.1109/COMPSAC65507.2025.00182},

isbn = {9798331574345 (ISBN)},

year  = {2025},

date = {2025-01-01},

pages = {1452–1461},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {There has been a significant rise in the use of Internet of Things (IoT) devices in recent years, but along with the increase in usage, there's also a rise in security vulnerabilities in the IoT software. The security vulnerabilities are difficult to find, and even more difficult to exploit dynamically. The software technologies, particularly used in the Samsung SmartThings environment, have a huge gap in terms of deprecated language usage, having a good testing environment and a security vulnerability scanning. This paper introduces a new tool, SmartTinkerer , filling these gaps by employing LLMs to translate deprecated language to new APIs, creating a digital twin simulating a virtual smart home device system for a testing environment and using reinforcement learning on the digital simulation to better scan for vulnerabilities. © 2025 Elsevier B.V., All rights reserved.},

keywords = {Artificial intelligence, Computer simulation languages, Digital devices, Digital Twins, Home testing, Intelligent buildings, Internet of thing, Internet of Things, Internet of things (IoT), Language Model, Large language model, large language model (LLM), Network Security, Reinforcement Learning, Reinforcement learnings, Security vulnerabilities, Smart homes, Software technology, Software Testing, Software testings, Testing environment, Virtual Reality},

pubstate = {published},

tppubtype = {inproceedings}

}