Rate My Professor Siamak Layeghy

Current research themes encompass large language and foundation models for security analytics and automation, adversarially robust and continual learning, and explainable machine learning for trustworthy deployment. Specific areas include advanced network and host-based intrusion detection systems using Transformers, Generative Adversarial Networks, and Transfer Learning; lightweight AI models for resource-constrained IoT devices and edge computing; and software-defined networking optimizations via programmable data planes like P4. Layeghy has secured notable funding, including the Advance Queensland Industry Research Fellowship (2020-2023) for AI-based cyber-attack detection in Queensland SMEs, ARC Discovery Projects (2025-2028), Energy Consumers Australia Influence Grants (2025-2027), and Innovation Connections grants. He has authored 72 works, with key publications such as 'FlowTransformer: A transformer framework for flow-based network intrusion detection systems' (2024, Expert Systems with Applications), 'Benchmarking the benchmark — Comparing synthetic and real-world Network IDS datasets' (2024, Journal of Information Security and Applications), 'eX-NIDS: A framework for explainable network intrusion detection leveraging Large Language Models' (2026, Computers and Electrical Engineering), 'An empirical evaluation of preprocessing methods for machine learning based network intrusion detection systems' (2025, Engineering Applications of Artificial Intelligence), and 'P4-Secure: in-band DDoS detection in software defined networks' (2025, IEEE Transactions on Network and Service Management). His scholarship has amassed over 4,400 citations on Google Scholar, underscoring its influence in cybersecurity and AI-driven network security.