Skip to main content

Research Repository

Advanced Search

Dr Thomas Tan's Outputs (123)

FedBT: Effective and Robust Federated Unlearning via Bad Teacher Distillation for Secure Internet of Things (2025)
Journal Article
Wang, F., Huo, J., Wang, W., Zhang, X., Liu, Y., Tan, Z., & Wang, C. (online). FedBT: Effective and Robust Federated Unlearning via Bad Teacher Distillation for Secure Internet of Things. IEEE Internet of Things Journal, https://doi.org/10.1109/JIOT.2025.3571432

Smart Internet of Things (IoT) devices generate vast, distributed data, and their limited computational and storage capacities complicate data protection. Federated Learning (FL) enables collaborative model training across clients, enhancing performa... Read More about FedBT: Effective and Robust Federated Unlearning via Bad Teacher Distillation for Secure Internet of Things.

Multi-Objective Evolutionary Algorithm for Automatic Generation of Adversarial Metamorphic Malware (2025)
Presentation / Conference Contribution
Babaagba, K. O., Wylie, J., Ayodele, M., & Tan, Z. (2024, September). Multi-Objective Evolutionary Algorithm for Automatic Generation of Adversarial Metamorphic Malware. Presented at 29th European Symposium on Research in Computer Security - SECAI, Bydgoszcz, Poland

The rise of metamorphic malware, a dangerous type of malware, has sparked growing research interest due to its increasing attacks on information assets and computer networks. Sophos’ recent threat report reveals that 94% of malware targeting organiza... Read More about Multi-Objective Evolutionary Algorithm for Automatic Generation of Adversarial Metamorphic Malware.

Multi-Agent Deep Reinforcement Learning-Based Cooperative Perception and Computation in VEC (2025)
Journal Article
Zhao, L., Li, L., Tan, Z., Hawbani, A., He, Q., & Liu, Z. (online). Multi-Agent Deep Reinforcement Learning-Based Cooperative Perception and Computation in VEC. IEEE Internet of Things Journal, https://doi.org/10.1109/jiot.2025.3546915

Connected and autonomous vehicles (CAVs) are an important paradigm of intelligent transportation systems. Cooperative perception (CP) and vehicular edge computing (VEC) enhance CAVs’ perception capacity of the region of interest (RoI) while alleviati... Read More about Multi-Agent Deep Reinforcement Learning-Based Cooperative Perception and Computation in VEC.

Dynamic Caching Dependency-Aware Task Offloading in Mobile EdgeComputing (2025)
Journal Article
Zhao, L., Zhao, Z., Hawbani, A., Liu, Z., Tan, Z., & Yu, K. (2025). Dynamic Caching Dependency-Aware Task Offloading in Mobile EdgeComputing. IEEE Transactions on Computers, 74(5), 1510-1523. https://doi.org/10.1109/tc.2025.3533091

Mobile Edge Computing (MEC) is a distributed computing paradigm that provides computing capabilities at the periphery of mobile cellular networks. This architecture empowers Mobile Users (MUs) to offload computation-intensive applications to large-sc... Read More about Dynamic Caching Dependency-Aware Task Offloading in Mobile EdgeComputing.

How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction (2024)
Presentation / Conference Contribution
Orme, M., Yu, Y., & Tan, Z. (2024, May). How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction. Presented at The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italy

This paper concerns the pressing need to understand and manage inappropriate language within the evolving human-robot interaction (HRI) landscape. As intelligent systems and robots transition from controlled laboratory settings to everyday households... Read More about How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction.

A Multi-UAV Cooperative Task Scheduling in Dynamic Environments: Throughput Maximization (2024)
Journal Article
Zhao, L., Li, S., Tan, Z., Hawbani, A., Timotheou, S., & Yu, K. (2025). A Multi-UAV Cooperative Task Scheduling in Dynamic Environments: Throughput Maximization. IEEE Transactions on Computers, 74(2), 442 - 454. https://doi.org/10.1109/tc.2024.3483636

Unmanned aerial vehicle (UAV) has been considered a promising technology for advancing terrestrial mobile computing in the dynamic environment. In this research field, throughput, the number of completed tasks and latency are critical evaluation indi... Read More about A Multi-UAV Cooperative Task Scheduling in Dynamic Environments: Throughput Maximization.

Graph Injection Attack based on Node Similarity and Non-linear Feature Injection Strategy (2024)
Presentation / Conference Contribution
Li, Q., Gao, Y., Wang, F., Wang, C., Babaagba, K. O., & Tan, Z. (2024, October). Graph Injection Attack based on Node Similarity and Non-linear Feature Injection Strategy. Presented at 20th EAI International Conference on Security and Privacy in Communication Networks, Dubai, United Arab Emirates

Graph Neural Networks (GNNs) exhibit promise in the domains of network analysis and recommendation systems. Notwithstanding , these networks are susceptible to node injection attacks. To mitigate this vulnerability, the academic community has put for... Read More about Graph Injection Attack based on Node Similarity and Non-linear Feature Injection Strategy.

PULRAS: A Novel PUF-Based Lightweight Robust Authentication Scheme (2024)
Presentation / Conference Contribution
Yaqub, Z., Yigit, Y., Maglaras, L., Tan, Z., & Wooderson, P. (2024, April). PULRAS: A Novel PUF-Based Lightweight Robust Authentication Scheme. Presented at The 20th Annual International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT 2024), Abu Dhabi, UAE

In the rapidly evolving landscape of Intelligent Transportation Systems (ITS), Vehicular Ad-hoc Networks (VANETs) play a critical role in enhancing road safety and traffic flow. However, VANETs face significant security and privacy challenges due to... Read More about PULRAS: A Novel PUF-Based Lightweight Robust Authentication Scheme.

Towards a cyberbullying detection approach: fine-tuned contrastive self-supervised learning for data augmentation (2024)
Journal Article
Al-Harigy, L. M., Al-Nuaim, H. A., Moradpoor, N., & Tan, Z. (2025). Towards a cyberbullying detection approach: fine-tuned contrastive self-supervised learning for data augmentation. International Journal of Data Science and Analytics, 19(3), 469-490. https://doi.org/10.1007/s41060-024-00607-9

Cyberbullying on social media platforms is pervasive and challenging to detect due to linguistic subtleties and the need for extensive data annotation. We introduce a Deep Contrastive Self-Supervised Learning (DCSSL) model that integrates a Natural L... Read More about Towards a cyberbullying detection approach: fine-tuned contrastive self-supervised learning for data augmentation.

Reliable and Fair Trustworthiness Evaluation Protocol for Platoon Service Recommendation System (2024)
Journal Article
Cheng, H., Tan, Z., Zhang, X., & Liu, Y. (2025). Reliable and Fair Trustworthiness Evaluation Protocol for Platoon Service Recommendation System. Chinese Journal of Electronics, 34(2), 563-575. https://doi.org/10.23919/cje.2023.00.012

Aiming at the problems of the communication inefficiency and high energy consumption in vehicular networks, the platoon service recommendation systems (PSRS) are presented. Many schemes for evaluating the reputation of platoon head vehicles have been... Read More about Reliable and Fair Trustworthiness Evaluation Protocol for Platoon Service Recommendation System.

Overtaking Feasibility Prediction for Mixed Connected and Connectionless Vehicles (2024)
Journal Article
Zhao, L., Qian, H., Hawbani, A., Al-Dubai, A. Y., Tan, Z., Yu, K., & Zomaya, A. Y. (2024). Overtaking Feasibility Prediction for Mixed Connected and Connectionless Vehicles. IEEE Transactions on Intelligent Transportation Systems, 25(10), 15065-15080. https://doi.org/10.1109/TITS.2024.3398602

Intelligent transportation systems (ITS) utilize advanced technologies to enhance traffic safety and efficiency, contributing significantly to modern transportation. The integration of Vehicle-to-Everything (V2X) further elevates road safety and fost... Read More about Overtaking Feasibility Prediction for Mixed Connected and Connectionless Vehicles.

MalSort: Lightweight and efficient image-based malware classification using masked self-supervised framework with Swin Transformer (2024)
Journal Article
Wang, F., Shi, X., Yang, F., Song, R., Li, Q., Tan, Z., & Wang, C. (2024). MalSort: Lightweight and efficient image-based malware classification using masked self-supervised framework with Swin Transformer. Journal of Information Security and Applications, 83, Article 103784. https://doi.org/10.1016/j.jisa.2024.103784

The proliferation of malware has exhibited a substantial surge in both quantity and diversity, posing significant threats to the Internet and indispensable network applications. The accurate and effective classification makes a pivotal role in defend... Read More about MalSort: Lightweight and efficient image-based malware classification using masked self-supervised framework with Swin Transformer.

Detection of Ransomware (2024)
Patent
Buchanan, B., McLaren, P., Russell, G., & Tan, Z. (2024). Detection of Ransomware. US20240152616A1

The present invention relates to a computer program product, a computing device and a method of detecting a file encrypted by ransomware by identifying a file write operation for a file on the computing device and determining if a predetermined numbe... Read More about Detection of Ransomware.

A Probability Mapping-Based Privacy Preservation Method for Social Networks (2024)
Presentation / Conference Contribution
Li, Q., Wang, Y., Wang, F., Tan, Z., & Wang, C. (2023, November). A Probability Mapping-Based Privacy Preservation Method for Social Networks. Presented at The 3rd International Conference on Ubiquitous Security 2023 (UbiSec-2023), Exeter

The mining and analysis of social networks can bring significant economic and social benefits. However, it also poses a risk of privacy leakages. Differential privacy is a de facto standard to prevent such leaks, but it suffers from the high sensitiv... Read More about A Probability Mapping-Based Privacy Preservation Method for Social Networks.

STIDNet: Identity-Aware Face Forgery Detection with Spatiotemporal Knowledge Distillation (2024)
Journal Article
Fang, M., Yu, L., Xie, H., Tan, Q., Tan, Z., Hussain, A., Wang, Z., Li, J., & Tian, Z. (2024). STIDNet: Identity-Aware Face Forgery Detection with Spatiotemporal Knowledge Distillation. IEEE Transactions on Computational Social Systems, 11(4), 5354 - 5366. https://doi.org/10.1109/tcss.2024.3356549

The impressive development of facial manipulation techniques has raised severe public concerns. Identity-aware methods, especially suitable for protecting celebrities, are seen as one of promising face forgery detection approaches with additional ref... Read More about STIDNet: Identity-Aware Face Forgery Detection with Spatiotemporal Knowledge Distillation.

Can Federated Models Be Rectified Through Learning Negative Gradients? (2024)
Presentation / Conference Contribution
Tahir, A., Tan, Z., & Babaagba, K. O. Can Federated Models Be Rectified Through Learning Negative Gradients?. Presented at 13th EAI International Conference, BDTA 2023, Edinburgh

Federated Learning (FL) is a method to train machine learning (ML) models in a decentralised manner, while preserving the privacy of data from multiple clients. However, FL is vulnerable to malicious attacks, such as poisoning attacks, and is challen... Read More about Can Federated Models Be Rectified Through Learning Negative Gradients?.

Challenges and Considerations in Data Recovery from Solid State Media: A Comparative Analysis with Traditional Devices (2023)
Presentation / Conference Contribution
Spalding, A., Tan, Z., & Babaagba, K. O. (2023, November). Challenges and Considerations in Data Recovery from Solid State Media: A Comparative Analysis with Traditional Devices. Presented at The International Symposium on Intelligent and Trustworthy Computing, Communications, and Networking (ITCCN-2023), Exeter, UK

Data recovery for forensic analysis of both hard drives and solid state media presents its own unique set of challenges. Hard drives face mechanical failures and data fragmentation , but their sequential storage and higher success rates make recovery... Read More about Challenges and Considerations in Data Recovery from Solid State Media: A Comparative Analysis with Traditional Devices.

Self-attention is What You Need to Fool a Speaker Recognition System (2023)
Presentation / Conference Contribution
Wang, F., Song, R., Tan, Z., Li, Q., Wang, C., & Yang, Y. (2023, November). Self-attention is What You Need to Fool a Speaker Recognition System. Presented at The 22nd IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom-2023), Exeter, UK

Speaker Recognition Systems (SRSs) are becoming increasingly popular in various aspects of life due to advances in technology. However, these systems are vulnerable to cyber threats, particularly adversarial attacks. Traditional adversarial attack me... Read More about Self-attention is What You Need to Fool a Speaker Recognition System.