Dr. Mirza Akhi

Dr. Mirza Akhi

PhD in Electronic and Computer Engineering | Healthcare IoT | Deep Learning

Publications

GAN-Driven Defense for Securing Autonomous Vehicles from Emerging Cyber Threats

Published in 2026 Global Conference on Wireless and Optical Technologies (GCWOT), 2026

This paper presents a Diffusion-GAN-based approach for detecting Distributed Denial of Service (DDoS) attacks in 5G-enabled autonomous vehicle environments. The proposed model combines diffusion-based latent conditioning with residual fusion to improve cyber threat detection in intelligent transportation systems.

Recommended citation: Mirza Akhi, Md Shalha Mucha Bhuiyan, Enrique Nava, Sanober Farheen Memon, Noorain Mukhtiar, Reenu Mohandas, and Lubna Luxmi Dhirani. (2026). "GAN-Driven Defense for Securing Autonomous Vehicles from Emerging Cyber Threats" GCWOT2026. https://ieeexplore.ieee.org/abstract/document/11499711

Dataset for DDoS Detection in 5G-Enabled Connected and Autonomous Vehicle Systems

Published in 2026 Global Conference on Wireless and Optical Technologies (GCWOT), 2026

This paper presents the UL-ECE-5G-AV-DDoS2025 dataset for analysing Distributed Denial-of-Service (DDoS) attacks in 5G-enabled Autonomous Vehicle (AV) environments. The dataset is generated using the CARLA simulator and includes both normal driving traffic and DDoS attack traffic under realistic 5G-connected scenarios.

Recommended citation: Mirza Akhi, Ciarán Eising, and Lubna Luxmi Dhirani. (2025). "Dataset for DDoS Detection in 5G-Enabled Connected and Autonomous Vehicle Systems" GCWOT2026. https://ieeexplore.ieee.org/abstract/document/11499550

Residual temporal CNNs for emerging cyber threat detection in healthcare IoT

Published in Discover Internet of Things, 2026

This paper presents a Residual-Temporal Convolutional Network (Res-TCN) model for detecting emerging cyber threats in Healthcare-IoT (H-IoT) environments. A realistic application-layer attack model is developed using the Cooja simulator to emulate wearable healthcare devices under Selective Forwarding (SF), Man-in-the-Middle (MITM), and Distributed Denial of Service (DDoS) attacks.

Recommended citation: Mirza Akhi, Ciarán Eising, and Lubna Luxmi Dhirani. (2026). "Residual temporal CNNs for emerging cyber threat detection in healthcare IoT." Discover Internet of Things. https://link.springer.com/article/10.1007/s43926-025-00271-w

Securing IoT Using Lightweight TCN for Edge Deployment on Raspberry Pi 4

Published in IEEE Open Journal of the Communications Society, 2025

This paper presents a lightweight Temporal Convolutional Network (TCN)-based method for edge deployment on Raspberry Pi 4 devices. The TCN-based approach leverages Healthcare-IoT (H-IoT) DDoS datasets and TensorFlow Lite (TFLite) optimization to enable efficient low-power attack detection in IoT environments.

Recommended citation: Mirza Akhi, Ciarán Eising, and Lubna Luxmi Dhirani. (2025). "Securing IoT Using Lightweight TCN for Edge Deployment on Raspberry Pi 4." IEEE Open Journal of the Communications Society. https://ieeexplore.ieee.org/abstract/document/11318643

Datasets for distributed denial-of-service detection in healthcare Internet of Things environments

Published in Data in Brief, 2025

This paper presents datasets for DDoS attack detection and mitigation in 5G-enabled Healthcare-IoT (H-IoT) environments. The datasets include realistic network traffic patterns generated from H-IoT devices using the Cooja and NS-3 simulators. They comprise labelled traffic samples representing both normal and malicious behaviour and support cybersecurity research in H-IoT and IoT environments.

Recommended citation: Mirza Akhi, Ciarán Eising, and Lubna Luxmi Dhirani. (2025). "Datasets for distributed denial-of-service detection in healthcare internet of things environments." Data in Brief. https://www.sciencedirect.com/science/article/pii/S2352340925009436

TCN-Based DDoS Detection and Mitigation in 5G Healthcare-IoT: A Frequency Monitoring and Dynamic Threshold Approach

Published in IEEE Access, 2025

This research presents a monitoring frequency-based detection and dynamic threshold mitigation method using Temporal Convolutional Networks (TCNs) in 5G Healthcare-IoT environments.

Recommended citation: Mirza Akhi, Ciarán Eising, and Lubna Luxmi Dhirani. (2025). "TCN-Based DDoS Detection and Mitigation in 5G Healthcare-IoT: A Frequency Monitoring and Dynamic Threshold Approach." IEEE Access. https://ieeexplore.ieee.org/iel8/6287639/6514899/10845749.pdf

Time Series Anomaly Detection with CNN for Environmental Sensors in Healthcare-IoT

Published in 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI), USA, 2024

This research develops a novel method utilizing Convolutional Neural Networks (CNNs) to detect anomalies in time series data from environmental sensors within Healthcare-IoT systems.

Recommended citation: Khatun, M. A., Bhattacharya, M., Eising, C., & Dhirani, L. L. (2024). "Time Series Anomaly Detection with CNN for Environmental Sensors in Healthcare-IoT." 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI). https://arxiv.org/pdf/2407.20695

Machine Learning for Healthcare-IoT Security: A Review and Risk Mitigation

Published in IEEE Access, 2023

This paper reviews and proposes risk mitigation strategies for security concerns in Healthcare-IoT systems using machine learning techniques.

Recommended citation: Mirza Akhi Khatun, Sanober Farheen Memon, Ciarán Eising, Lubna Luxmi Dhirani. (2023). "Machine Learning for Healthcare-IoT Security: A Review and Risk Mitigation." IEEE Access. 11. https://www.researchgate.net/publication/376763490_Machine_Learning_for_Healthcare-IoT_Security_A_Review_and_Risk_Mitigation

Development of Cyber Attack Model for Private Network

Published in 2022 Second International Conference on Interdisciplinary Cyber Physical Systems (ICPS), 2022

This paper delves into the development and intricacies of a cyber attack model tailored for private networks.

Recommended citation: M. Al-Amin, M. A. Khatun and M. Nasir Uddin, 'Development of Cyber Attack Model for Private Network,' 2022 Second International Conference on Interdisciplinary Cyber Physical Systems (ICPS), Chennai, India, 2022, pp. 216-221, doi: 10.1109/ICPS55917.2022.00046. https://ieeexplore.ieee.org/abstract/document/9941250

Malicious Nodes Detection based on Artificial Neural Network in IoT Environments

Published in 2019 22nd International Conference on Computer and Information Technology (ICCIT), 2019

This study employs the Artificial Neural Network (ANN) to detect malicious nodes in IoT environments, addressing security concerns of embedded devices. The method discerns usual and malicious patterns, achieving a detection accuracy of 77.51%.

Recommended citation: M. A. Khatun, N. Chowdhury and M. N. Uddin, "Malicious Nodes Detection based on Artificial Neural Network in IoT Environments," 2019 22nd International Conference on Computer and Information Technology (ICCIT), Dhaka, Bangladesh, 2019, pp. 1-6, doi: 10.1109/ICCIT48885.2019.9038563. https://ieeexplore.ieee.org/document/9038563