Kahraman Kostas
I hold a PhD in Computer Science from the School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh, where my research focused on IoT security, particularly device identification and attack detection. My broader interests include computer networks, indoor positioning, and the practical applications of machine learning. I previously worked as a Researcher at Huawei's Edinburgh R&D Centre, where I developed machine learning solutions for indoor positioning using geospatial data.
I hold an MSc in Computer Networks and Security (Distinction) from the University of Essex, with my thesis centered on using machine learning for network attack detection (Supervised by Martin Reed). My undergraduate background is in Computer Education and Instructional Technology from Marmara University.
Before pursuing graduate studies, I spent seven years teaching computer science in Turkey and contributed to national education projects, including the Fatih Project, which aimed to integrate technology into public education. I am currently a National Education Specialist at the Ministry of National Education, focusing on educational systems for overseas students.
In addition to my professional work, I have a keen interest in Turkish literature, etymology, classical poetry, hiking, and photography.
News
| NOV 2024 | Our new paper ready for publication (GeMID: Generalizable Models for Device Identification in IoT Networks). |
| SEP 2024 | I have started a new position as a National Education Specialist at the Directorate General of Higher Education and Overseas Education. |
| JUN 2024 | Our new paper ready for publication (Individual Packet Features are a Risk to Model Generalisation in ML-Based Intrusion Detection). |
| APR 2024 | I gave a career talk on Cyber Security in the program hosted by Edinburgh Education Attaché Office (Turkish). |
| MAR 2024 | New publication🎉 Our (With RYK) paper has been accepted to Journal of Clinical and Experimental Neuropsychology (JCEN). |
| OCT 2023 | Successfully defended my thesis! 🎉 Passed with minor corrections📚🎓. |
| OCT 2023 | New IoT Attack Detection paper (IoTGeM) ready for publication. |
| SEP 2023 | I submitted my PhD thesis. My viva is on October 31st!👻🎃🍬🦇💀🔮🕸👻 |
| JULY 2023 | New device identification paper ready for publication. |
| NOW 2022 | I was a finalist of the Huawei Tech Arena - Enter The Metaverse (6th position -Best AI approach) Solving 3D graphics compression for efficient Metaverse architecture. (w RYK) |
| JUN 2022 | Our paper has been accepted to the IEEE IoT Journal. |
| MAY 2022 | Our (With RYK and Huawei RD Indoor Positioning Team) paper has been accepted to the IPIN 2022 conference. |
| FEB 2022 | I have joined Huawei UK RD Edinburgh Lab. I am creating solutions to indoor positioning problems by focusing on the analysis of geospatial data with machine learning. |
| JAN 2022 | Our success in the national competition was reported in a newspaper. |
| DEC 2021 | I won Huawei UK University Challenge Competition 2021. (with RYK) |
Publications
Individual Packet Features are a Risk to Model Generalisation in ML-Based Intrusion Detection
Kahraman Kostas, Mike Just, Michael A. Lones, arXiv, 2024
[paper][code]
Semantic verbal fluency in native speakers of Turkish: A systematic review of category use, scoring metrics and normative data in healthy individuals
Rabia Yasa Kostas, Kahraman Kostas, Sarah E MacPherson, Maria K Wolters, JCEN, 2024
[paper]
IoTGeM: Generalisable Models for Behaviour-Based IoT Attack Detection
Kahraman Kostas, Mike Just, Michael A. Lones, arXiv, 2023
[paper][code]
Externally validating the IoTDevID device identification methodology using the CIC IoT 2022 Dataset
Kahraman Kostas, Mike Just, Michael A. Lones, arXiv, 2023
[paper][code]
LSTM based IoT Device Identification
Kahraman Kostas, arXiv, 2023
[paper][code]
CNN based IoT Device Identification
Kahraman Kostas, arXiv, 2023
[paper][code]
WiFi Based Distance Estimation Using Supervised Machine Learning
Kahraman Kostas, Rabia Yasa Kostas, Francisco Zampella, Firas Alsehly, IEEE, IPIN, 2022
[paper][code]
IoTDevID: A behavior-based device identification method for the IoT
Kahraman Kostas, Mike Just, Michael A. Lones, IEEE, IoT Journal, 2022
[paper][code]
IoTDevID: A behaviour-based fingerprinting method for device identification in the IoT
Kahraman Kostas, Mike Just, Michael A. Lones, arXiv, 2021
[paper][code]
Anomaly Detection in Networks Using Machine Learning
Kahraman Kostas arXiv, 2018
[paper][code]
Teaching
Advanced Network Security, Heriot-Watt University
Teaching Assistant, Mike Just, 2021 & 2022
Computer Network Security, Heriot-Watt University
Teaching Assistant, Mike Just, 2020 & 2021
Software Development 1 (JAVA), Heriot-Watt University
Teaching Assistant, Michael Lones, 2020
Data Communications and Networking, Heriot-Watt University
Teaching Assistant, Idris Skloul Ibrahim, 2020