Overview
Background
Opportunities for Students
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.
Why Join My Group?
My research is inherently interdisciplinary, bridging AI, cybersecurity, and networking to address real-world problems. Students will work on cutting-edge projects with access to UQ’s world-class facilities and opportunities to collaborate with global experts. Whether you’re interested in defending against cyber threats or shaping the future of IoT and SDN, my group provides a dynamic environment to grow as a researcher.
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
2023
Journal Article
HARBIC: Human activity recognition using bi-stream convolutional neural network with dual joint time-frequency representation
Hosseininoorbin, Seyedehfaezeh, Layeghy, Siamak, Kusy, Brano, Jurdak, Raja and Portmann, Marius (2023). HARBIC: Human activity recognition using bi-stream convolutional neural network with dual joint time-frequency representation. Internet of Things, 22 100816, 1-17. doi: 10.1016/j.iot.2023.100816
2023
Journal Article
Exploring Edge TPU for deep feed-forward neural networks
Hosseininoorbin, Seyedehfaezeh, Layeghy, Siamak, Kusy, Brano, Jurdak, Raja and Portmann, Marius (2023). Exploring Edge TPU for deep feed-forward neural networks. Internet of Things, 22 100749, 1-16. doi: 10.1016/j.iot.2023.100749
2023
Journal Article
XG-BoT: an explainable deep graph neural network for botnet detection and forensics
Lo, Wai Weng, Kulatilleke, Gayan, Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). XG-BoT: an explainable deep graph neural network for botnet detection and forensics. Internet of Things, 22 100747, 100747. doi: 10.1016/j.iot.2023.100747
2023
Other Outputs
NF-BoT-IoT
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-BoT-IoT. The University of Queensland. (Dataset) doi: 10.48610/62e6d80
2023
Other Outputs
CIC-BoT-IoT
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marus (2023). CIC-BoT-IoT. The University of Queensland. (Dataset) doi: 10.48610/c80fccd
2023
Other Outputs
NF-UNSW-NB15-v2
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-UNSW-NB15-v2. The University of Queensland. (Dataset) doi: 10.48610/ffbb0c1
2023
Other Outputs
NF-ToN-IoT
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-ToN-IoT. The University of Queensland. (Dataset) doi: 10.48610/2fa2ed6
2023
Other Outputs
NF-UQ-NIDS-v2
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-UQ-NIDS-v2. The University of Queensland. (Dataset) doi: 10.48610/631a24a
2023
Other Outputs
NF-UNSW-NB15
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-UNSW-NB15. The University of Queensland. (Dataset) doi: 10.48610/5d0832d
2023
Other Outputs
NF-ToN-IoT-v2
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-ToN-IoT-v2. The University of Queensland. (Dataset) doi: 10.48610/38a2d07
2023
Other Outputs
NF-UQ-NIDS
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-UQ-NIDS. The University of Queensland. (Dataset) doi: 10.48610/69b5a53
2023
Other Outputs
CIC-ToN-IoT
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). CIC-ToN-IoT. The University of Queensland. (Dataset) doi: 10.48610/f6884ce
2023
Other Outputs
NF-BoT-IoT-v2
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-BoT-IoT-v2. The University of Queensland. (Dataset) doi: 10.48610/ec73920
2023
Conference Publication
DOC-NAD: A hybrid deep one-class classifier for network anomaly detection
Sarhan, Mohanad, Kulatilleke, Gayan, Lo, Wai Weng, Layeghy, Siamak and Portmann, Marius (2023). DOC-NAD: A hybrid deep one-class classifier for network anomaly detection. 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW), Bangalore, India, 1 - 4 May 2023. Piscataway, NJ, United States: IEEE. doi: 10.1109/ccgridw59191.2023.00016
2023
Journal Article
From zero-shot machine learning to zero-day attack detection
Sarhan, Mohanad, Layeghy, Siamak, Gallagher, Marcus and Portmann, Marius (2023). From zero-shot machine learning to zero-day attack detection. International Journal of Information Security, 22 (4), 947-959. doi: 10.1007/s10207-023-00676-0
2023
Journal Article
Inspection-L: self-supervised GNN node embeddings for money laundering detection in bitcoin
Lo, Wai Weng, Kulatilleke, Gayan K., Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). Inspection-L: self-supervised GNN node embeddings for money laundering detection in bitcoin. Applied Intelligence, 53 (16), 1-12. doi: 10.1007/s10489-023-04504-9
2023
Other Outputs
NF-CSE-CIC-IDS2018-v2
Sarhan, Mohanad, Layeghy, Siamak and Portmann, Marius (2023). NF-CSE-CIC-IDS2018-v2. The University of Queensland. (Dataset) doi: 10.48610/e9636b7
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
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
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
Funding
Current funding
Past funding
Supervision
Availability
- Dr Siamak Layeghy is:
- Available for supervision
Before you email them, read our advice on how to contact a supervisor.
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
Towards Practical Machine Learning Based Network Intrusion Detection
Associate Advisor
Other advisors: Associate Professor Marcus Gallagher, Professor Marius Portmann
-
Doctor Philosophy
Low-energy LoRaWAN-based automatic and continuous measurement of organisational environmental performance.
Associate Advisor
Other advisors: Professor Sara Dolnicar, 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 Sara Dolnicar, Professor Marius Portmann
Completed supervision
-
2023
Doctor Philosophy
Deep Learning at the Edge: Exploring in-situ Classification in IoT
Associate Advisor
Other advisors: Professor Marius Portmann
-
2023
Doctor Philosophy
The Detection of Network Cyber Attacks Using Machine Learning
Associate Advisor
Other advisors: Associate Professor Marcus Gallagher, Professor Marius Portmann
-
2023
Master Philosophy
Graph Representation Learning for Cyberattack Detection and Forensics
Associate Advisor
Other advisors: Associate Professor Marcus Gallagher, Professor Marius Portmann
Media
Enquiries
For media enquiries about Dr Siamak Layeghy's areas of expertise, story ideas and help finding experts, contact our Media team: