Skip to menu Skip to content Skip to footer
Dr Siamak Layeghy
Dr

Siamak Layeghy

Email: 
Phone: 
+61 7 334 61471

Overview

Background

I am keen to supervise motivated postgraduate and PhD students who are passionate about AI, cybersecurity, or networking. My research group offers hands-on projects, including developing AI-driven intrusion detection systems, securing IoT ecosystems, and optimising SDN frameworks. Students will gain experience with state-of-the-art ML tools, collaborate with industry partners, and contribute to high-impact publications. Ideal candidates should have strong programming skills (e.g., Python, C++) and a basic understanding of ML or networking concepts, though enthusiasm and a willingness to learn are equally valued.

About Me

As a passionate researcher at The University of Queensland, I explore the intersection of Artificial Intelligence (AI) and Machine Learning (ML) with cutting-edge applications in cybersecurity, Internet of Things (IoT), and Software Defined Networking (SDN). My work focuses on developing innovative, real-world solutions to protect digital systems and optimise network performance, mentoring the next generation of researchers to tackle global challenges.

Availability

Dr Siamak Layeghy is:
Available for supervision

Qualifications

  • Doctor of Philosophy, The University of Queensland

Research interests

  • AI/ML for Cybersecurity

    I develop advanced intrusion detection systems (NIDS and HIDS) using techniques like Transformers, Generative Adversarial Networks (GANs), and Transfer Learning to detect and mitigate cyber threats in real time.

  • Edge Learning and IoT Security

    My work focuses on lightweight AI models for resource-constrained IoT devices, enabling secure and efficient edge computing.

  • Software Defined Networking (SDN)

    I explore network optimisation and programmable data planes (e.g., P4) to enhance Quality of Service (QoS) and constrained routing for next-generation networks.

Research impacts

Research Vision

My research leverages AI and ML to secure and optimise emerging technologies. By combining advanced techniques like Large Language Models (LLMs), Graph Neural Networks (GNNs), and Federated Learning with practical applications, I aim to create robust, scalable systems for network security, edge computing, and programmable networks. My goal is to address pressing challenges in cybersecurity and IoT, ensuring safe and efficient digital ecosystems.

My Google Scholar: https://scholar.google.com.au/citations?user=uB6MlpQAAAAJ&hl=en

Works

Search Professor Siamak Layeghy’s works on UQ eSpace

72 works between 2011 and 2026

41 - 60 of 72 works

2023

Other Outputs

NF-CSE-CIC-IDS2018

Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-CSE-CIC-IDS2018. The University of Queensland. (Dataset) doi: 10.48610/b9ed88b

NF-CSE-CIC-IDS2018

2022

Journal Article

Anomal-E: A self-supervised network intrusion detection system based on graph neural networks

Caville, Evan, Lo, Wai Weng, Layeghy, Siamak and Portmann, Marius (2022). Anomal-E: A self-supervised network intrusion detection system based on graph neural networks. Knowledge-Based Systems, 258 110030, 1-11. doi: 10.1016/j.knosys.2022.110030

Anomal-E: A self-supervised network intrusion detection system based on graph neural networks

2022

Conference Publication

Network intrusion detection system in a light bulb

Manocchio, Liam Daly, Layeghy, Siamak and Portmann, Marius (2022). Network intrusion detection system in a light bulb. 32nd International Telecommunication Networks and Applications Conference (ITNAC), Wellington, New Zealand, 30 November- 2 December 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/itnac55475.2022.9998371

Network intrusion detection system in a light bulb

2022

Journal Article

Evaluating Standard Feature Sets Towards Increased Generalisability and Explainability of ML-Based Network Intrusion Detection

Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2022). Evaluating Standard Feature Sets Towards Increased Generalisability and Explainability of ML-Based Network Intrusion Detection. Big Data Research, 30 100359, 1-9. doi: 10.1016/j.bdr.2022.100359

Evaluating Standard Feature Sets Towards Increased Generalisability and Explainability of ML-Based Network Intrusion Detection

2022

Journal Article

Cyber threat intelligence sharing scheme based on federated learning for network intrusion detection

Sarhan, Mohanad, Layeghy, Siamak, Moustafa, Nour and Portmann, Marius (2022). Cyber threat intelligence sharing scheme based on federated learning for network intrusion detection. Journal of Network and Systems Management, 31 (1) 3. doi: 10.1007/s10922-022-09691-3

Cyber threat intelligence sharing scheme based on federated learning for network intrusion detection

2022

Journal Article

HBFL: a hierarchical blockchain-based federated learning framework for collaborative IoT intrusion detection

Sarhan, Mohanad, Lo, Wai Weng, Layeghy, Siamak and Portmann, Marius (2022). HBFL: a hierarchical blockchain-based federated learning framework for collaborative IoT intrusion detection. Computers and Electrical Engineering, 103 108379, 1-17. doi: 10.1016/j.compeleceng.2022.108379

HBFL: a hierarchical blockchain-based federated learning framework for collaborative IoT intrusion detection

2022

Conference Publication

Graph neural network-based android malware classification with jumping knowledge

Lo, Wai Weng, Layeghy, Siamak, Sarhan, Mohanad, Gallagher, Marcus and Portmann, Marius (2022). Graph neural network-based android malware classification with jumping knowledge. 2022 IEEE Conference on Dependable and Secure Computing (DSC), Edinburgh, United Kingdom, 22-24 June 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers . doi: 10.1109/dsc54232.2022.9888878

Graph neural network-based android malware classification with jumping knowledge

2022

Conference Publication

E-GraphSAGE: a graph neural network based intrusion detection system for IoT

Lo, Wai Weng, Layeghy, Siamak, Sarhan, Mohanad, Gallagher, Marcus and Portmann, Marius (2022). E-GraphSAGE: a graph neural network based intrusion detection system for IoT. NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium, Budapest, Hungary, 25-29 April 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers . doi: 10.1109/noms54207.2022.9789878

E-GraphSAGE: a graph neural network based intrusion detection system for IoT

2022

Book Chapter

SCOR: a constraint programming approach to software defined networking

Layeghy, Siamak and Portmann, Marius (2022). SCOR: a constraint programming approach to software defined networking. Horizons in computer science research. Volume 22. (pp. 141-191) edited by Thomas S. Clary. New York, NY United States: Nova Science Publishers.

SCOR: a constraint programming approach to software defined networking

2021

Journal Article

Towards a standard feature set for network intrusion detection system datasets

Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2021). Towards a standard feature set for network intrusion detection system datasets. Mobile Networks and Applications, 27 (1), 357-370. doi: 10.1007/s11036-021-01843-0

Towards a standard feature set for network intrusion detection system datasets

2021

Conference Publication

FlowGAN - Synthetic Network Flow Generation using Generative Adversarial Networks

Manocchio, Liam Daly, Layeghy, Siamak and Portmann, Marius (2021). FlowGAN - Synthetic Network Flow Generation using Generative Adversarial Networks. International Conference on Computational Science and Engineering (CSE), Shenyang, China, 20-22 October 2021. Piscataway, NJ, United States: IEEE. doi: 10.1109/cse53436.2021.00033

FlowGAN - Synthetic Network Flow Generation using Generative Adversarial Networks

2021

Journal Article

Deep learning-based cattle behaviour classification using joint time-frequency data representation

Hosseininoorbin, Seyedehfaezeh, Layeghy, Siamak, Kusy, Brano, Jurdak, Raja, Bishop-Hurley, Greg J., Greenwood, Paul L and Portmann, Marius (2021). Deep learning-based cattle behaviour classification using joint time-frequency data representation. Computers and Electronics in Agriculture, 187 106241, 106241. doi: 10.1016/j.compag.2021.106241

Deep learning-based cattle behaviour classification using joint time-frequency data representation

2021

Journal Article

Automatic fetal movement recognition from multi-channel accelerometry data

Mesbah, Mostefa, Khlif, Mohamed Salah, Layeghy, Siamak, East, Christine E., Dong, Shiying, Brodtmann, Amy, Colditz, Paul B. and Boashash, Boualem (2021). Automatic fetal movement recognition from multi-channel accelerometry data. Computer Methods and Programs in Biomedicine, 210 106377, 106377. doi: 10.1016/j.cmpb.2021.106377

Automatic fetal movement recognition from multi-channel accelerometry data

2021

Conference Publication

Scaling Spectrogram Data Representation for Deep Learning on Edge TPU

Hosseininoorbin, Seyedehfaezeh, Layeghy, Siamak, Kusy, Brano, Jurdak, Raja and Portmann, Marius (2021). Scaling Spectrogram Data Representation for Deep Learning on Edge TPU. 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), Kassel, Germany, 22-26 March 2021. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers Inc.. doi: 10.1109/PerComWorkshops51409.2021.9431041

Scaling Spectrogram Data Representation for Deep Learning on Edge TPU

2021

Conference Publication

NetFlow datasets for machine learning-based network intrusion detection systems

Sarhan, Mohanad, Layeghy, Siamak, Moustafa, Nour and Portmann, Marius (2021). NetFlow datasets for machine learning-based network intrusion detection systems. 10th EAI International Conference, BDTA 2020 and 13th EAI International Conference on Wireless Internet, WiCON 2020, Virtual Event, 11 December 2020. Cham, Switzerland: Springer Science and Business Media Deutschland GmbH. doi: 10.1007/978-3-030-72802-1_9

NetFlow datasets for machine learning-based network intrusion detection systems

2020

Journal Article

P-SCOR: integration of constraint programming orchestration and programmable data plane

Melis, Andrea, Layeghy, Siamak, Berardi, Davide, Portmann, Marius, Prandini, Marco and Callegati, Franco (2020). P-SCOR: integration of constraint programming orchestration and programmable data plane. IEEE Transactions on Network and Service Management, 18 (1) 9311177, 1-1. doi: 10.1109/tnsm.2020.3048277

P-SCOR: integration of constraint programming orchestration and programmable data plane

2019

Conference Publication

Enhancing quality of experience of VoIP traffic in SDN based end-hosts

Al-Najjar, Anees, Layeghy, Siamak, Portmann, Marius and Indulska, Jadwiga (2019). Enhancing quality of experience of VoIP traffic in SDN based end-hosts. 28th International Telecommunication Networks and Applications Conference, ITNAC 2018, Sydney, NSW Australia, 21-23 November 2018. New York, NY USA: Institute of Electrical and Electronics Engineers. doi: 10.1109/ATNAC.2018.8615286

Enhancing quality of experience of VoIP traffic in SDN based end-hosts

2018

Other Outputs

SCOR: Software-defined Constrained Optimal Routing Platform for SDN

Layeghy, Siamak (2018). SCOR: Software-defined Constrained Optimal Routing Platform for SDN. PhD Thesis, School of Information Technology and Electrical Engineering, The University of Queensland. doi: 10.14264/uql.2018.820

SCOR: Software-defined Constrained Optimal Routing Platform for SDN

2018

Journal Article

Flow-level load balancing of HTTP traffic using open flow

Al-Najjar, Anees, Layeghy, Siamak, Portmann, Marius and Indulska, Jadwiga (2018). Flow-level load balancing of HTTP traffic using open flow. Australian Journal of Telecommunications and the Digital Economy, 6 (4), 75-95. doi: 10.18080/ajtde.v6n4.166

Flow-level load balancing of HTTP traffic using open flow

2017

Journal Article

A new QoS routing northbound interface for SDN

Layeghy, Siamak, Pakzad, Farzaneh and Portmann, Marius (2017). A new QoS routing northbound interface for SDN. Australian Journal of Telecommunications and the Digital Economy, 5 (1), 92-115. doi: 10.18080/ajtde.v5n1.91

A new QoS routing northbound interface for SDN

Funding

Current funding

  • 2025 - 2028
    Mechanisms of Behaviour Change Theory
    ARC Discovery Projects
    Open grant
  • 2024 - 2025
    Customer electricity usage segmentation based on smart meter data
    Energy Queensland Limited
    Open grant

Past funding

  • 2024
    Using NLP for the implementation of Host-based Intrusion Detection
    Research Donation Generic
    Open grant
  • 2020 - 2023
    AI- based Cyber-Attack Detection and Response System for Queensland based SMEs
    Advance Queensland Industry Research Fellowships
    Open grant
  • 2019
    Machine Learning for Automated Network Anomaly Detection, Cyber Security and Analysis - Phase II
    Innovation Connections
    Open grant
  • 2018 - 2019
    Machine Learning for Automated Network Anomaly detection and Analysis
    Innovation Connections
    Open grant

Supervision

Availability

Dr Siamak Layeghy is:
Available for supervision

Looking for a supervisor? Read our advice on how to choose a supervisor.

Available projects

  • Machine Learning for Computer Networking

    This project aims to harness Machine Learning and AI techniques, with a focus on Large Language Models, for the configuration and management of Computer Networks.

    Your application will be assessed on a competitive basis.

    We take into account your:

    • previous academic record
    • publication record
    • honours and awards
    • employment history

    A working knowledge of AI, software engineering and data science would be of benefit to someone working on this project.

    You will demonstrate academic achievement in the field/s of computer networking and machine learning and the potential for scholastic success.

    A background or knowledge of Large Language Models (LLMs) is highly desirable. You apply for this scholarship when you submit an application for your program. You don’t need to submit a separate scholarship application.

Supervision history

Current supervision

  • Doctor Philosophy

    Enhancing the Privacy-Preserving ML techniques with Functional Encryption approach

    Principal Advisor

    Other advisors: Professor Marius Portmann

  • Doctor Philosophy

    Machine Learning for Improving Services and Management of Software Defined Networks

    Principal Advisor

    Other advisors: Professor Marius Portmann

  • Doctor Philosophy

    Enhancing Cyberbullying Detection in Arabic Social Media through Explainable AI and Natural Language Processing: A Human-Centric Approach

    Principal Advisor

    Other advisors: Professor Marius Portmann

  • Doctor Philosophy

    Low-energy LoRaWAN-based automatic and continuous measurement of organisational environmental performance.

    Associate Advisor

    Other advisors: Professor Marius Portmann

  • Doctor Philosophy

    eXtended Management Network System (xNMS)

    Associate Advisor

    Other advisors: Professor Marius Portmann

  • Doctor Philosophy

    Exploring the Capabilities of LoRaWAN IoT Technology for Multisensor Data Collection and Analysis

    Associate Advisor

    Other advisors: Professor Marius Portmann

  • Doctor Philosophy

    Adaptive Model Compression for Efficient Multimodal Foundation Models

    Associate Advisor

    Other advisors: Associate Professor Mahsa Baktashmotlagh

  • Doctor Philosophy

    Towards Practical Machine Learning Based Network Intrusion Detection

    Associate Advisor

    Other advisors: Associate Professor Marcus Gallagher, Professor Marius Portmann

Completed supervision

Media

Enquiries

For media enquiries about Dr Siamak Layeghy's areas of expertise, story ideas and help finding experts, contact our Media team:

communications@uq.edu.au