Dr. Kahraman Kostas - Default Dr. Kahraman Kostas - Hover

Kahraman Kostas, PhD

Computer Science Researcher specializing in IoT Security, Generalisable Machine Learning, and Network Forensics.

I hold a PhD in Computer Science from Heriot-Watt University, Edinburgh. Bridging the gap between theoretical ML models and real-world deployment, my research addresses a fundamental challenge in IoT security: the lack of generalisable models for device identification and intrusion detection.

Research & Impact

My doctoral thesis, “Behaviour-based Security with Machine Learning on IoT Networks,” (Supervisors: Dr. Mike Just & Dr. Michael Lones) systematically demonstrated how conventional feature representations hinder model generalisation.

To solve this, I developed novel frameworks—IoTDevID, GeMID, and IoTGeM—explicitly designed to remain robust across unseen devices and changing network conditions. This work has been published in top-tier venues including:

  • IEEE Internet of Things Journal (Q1)
  • Computer Networks (Q1)
  • Internet of Things Journal -Elsevier- (Q1)
  • IEEE Networking Letters (Q1)

Industry & Applied Experience

Huawei R&D (Edinburgh): During my PhD, I worked as a Researcher at the Huawei UK R&D Centre. I developed ML solutions for community detection and WiFi-based distance estimation, strengthening my ability to build industry-scale systems. Prior to this, my team won 1st place in the Huawei UK University Challenge (2021) for our work on indoor localisation, which we later published at the prestigious IEEE IPIN conference.

Large-Scale Technical Leadership (Current Role): Since September 2024, I have been serving as a National Education Expert at the Turkish Ministry of National Education. In this capacity, I act as the Technical Lead and Architect for the “Ulkem Yanımda” project.

I coordinated the technical infrastructure design and deployment of this international platform, which connects 100+ teachers with 2000+ students across 10+ countries. My role involves managing full-stack operations, data analytics, and cross-border coordination to ensure sustainable scalability.

Background

I hold an MSc in Computer Networks and Security (Distinction) from the University of Essex. My interdisciplinary background, including degrees in Computer Education (Marmara Univ.) and Literature, informs my keen interest in explainable AI and research communication.

🚀 Open for Collaborations: I am actively seeking Postdoctoral Research positions in IoT security, applied ML, and data-driven systems. I am particularly interested in labs that value rigorous methodological analysis combined with real-world deployment. Please get in touch to discuss opportunities.

Outside the lab, I am passionate about Turkish literature, etymology, classical poetry, hiking, and photography.

News

OCT 2025
Our (With RYK) paper "GeMID: Generalizable Models for IoT Device Identification" has been accepted for publication in the Elsevier IoT journal.
JUL 2025
Our paper, "IoTGeM: Generalizable Models for Behaviour-Based IoT Attack Detection" has been accepted for publication in the Computer Networks journal.
JUN 2025
Our (With RYK) paper "Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories" has been accepted to the IPIN 2025 conference.
JAN 2025
New publication🎉 Our paper (Individual Packet Features are a Risk to Model Generalisation in ML-Based Intrusion Detection) has been accepted to IEEE Networking Letters.
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.
MORE
For older news please click [here]

Publications

GeMID: Generalizable Models for IoT Device Identification
K Kostas, R Yasa Kostas, M Just, MA Lones
Elsevier Internet of Things Journal, 2025
IoTGeM: Generalisable Models for Behaviour-Based IoT Attack Detection
Kahraman Kostas, Mike Just, Michael A. Lones
Computer Networks, 2025
Individual Packet Features are a Risk to Model Generalisation in ML-Based Intrusion Detection
Kahraman Kostas, Mike Just, Michael A. Lones
IEEE Networking Letters, 2025
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
For more publication please click [here]

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