Topic 1: Metaverse
Motivation: The Metaverse, envisioned as a collective virtual shared space, is emerging at the confluence of various advanced technologies, including virtual and augmented reality, blockchain, and artificial intelligence. This digital realm promises an unprecedented level of integration between virtual environments and the physical world, offering new dimensions to social interactions, economic transactions, and digital identities. However, the ambitious development of the Metaverse brings forth significant technical challenges, such as creating interoperable and scalable virtual spaces, ensuring real-time interactions with minimal latency, and developing secure and transparent systems for digital assets and identities. These technical hurdles underscore the urgent need for focused research to address the complexities of building a seamless, accessible, and secure Metaverse. Such research is crucial not only for unlocking the full potential of these virtual spaces but also for anticipating and mitigating the social, ethical, and security implications that accompany the creation of such expansive digital universes.
Recent journal papers from our group on this topic:
D. Tulone, D. T. Hoang, A. Puliafito, W. Y. B. Lim and P. Henz, "Design criteria and technical requirements for sustainable metaverse ecosystems," Technical Specification ITU FGMV-08, Oct. 2023.
N. Q. Hieu*, D. T. Hoang, D. N. Nguyen, V. D. Nguyen, Y. Xiao, and E. Dutkiewicz, "Enhancing immersion and presence in the Metaverse with over-the-air brain-computer interface," IEEE TWC, under review.
N. Q. Hieu*, D. T. Hoang, D. N. Nguyen, and M. A. Alsheikh, "Reconstructing Human Pose from Inertial Measurements: A Generative Model-based Compressive Sensing Approach," IEEE Journal on Selected Areas in Communications, accepted 2024.
H. Y. Zhu, N. Q. Hieu*, D. T. Hoang, D. N. Nguyen, C. T. Lin, "A human-centric metaverse enabled by brain-computer interface: A survey", IEEE COMST, accepted 2024.
D. T. Hoang, D. N. Nguyen, C. T. Nguyen*, E. Hossain, and D. Niyato, edt., Metaverse Communication and Computing Networks: Applications, Technologies, and Approaches. IEEE-Wiley, 2023.
C. T. Nguyen*, D. T. Hoang, D. N. Nguyen, Y. Xiao, D. Niyato, and E. Dutkiewicz, "MetaShard: A novel sharding blockchain platform for Metaverse applications," IEEE Transactions on Mobile Computing, accepted 2023.
N. H. Chu*, D. T. Hoang, D. N. Nguyen, K. T. Phan, E. Dutkiewicz, D. Niyato, and T. Shu "MetaSlicing: A novel resource allocation framework for Metavserse," IEEE Transactions on Mobile Computing, accepted 2023.
N. Q. Hieu*, D. N. Nguyen, D. T. Hoang, and E. Dutkiewicz, "When virtual reality meets rate splitting multiple access: A joint communication and computation approach," IEEE Journal on Selected Areas in Communications, vol. 41, no. 5, pp. 1536-1548, May 2023.
Topic 2: Machine Learning for Cyberattack Detection
Motivation: Cyberattacks are a serious threat to the security and privacy of information systems and networks. They can cause significant damage to individuals, organizations, and society by compromising data, disrupting services, and stealing resources. To prevent and mitigate cyberattacks, various methods have been proposed to detect and classify them in real time. Among these methods, machine learning (ML) has emerged as a powerful and effective technique, as it can learn from data and adapt to changing environments. However, applying ML to cyberattack detection also poses many technical challenges, such as dealing with imbalanced and noisy data, selecting appropriate features and algorithms, ensuring robustness and scalability, and providing explainability and trustworthiness. These challenges require novel solutions and rigorous research from different disciplines and perspectives. Therefore, the research on machine learning for cyberattack detection is motivated by both the practical need to enhance cybersecurity and the scientific interest to advance ML theory and applications.
Recent journal papers from our group on this topic:
T. V. Khoa*, et al., "Securing Blockchain Systems: A Novel Collaborative Learning Framework to Detect Attacks in Transactions and Smart Contracts," under review.
P. V. Dinh*, Q. U. Nguyen, D. T. Hoang, D. N. Nguyen, S. P. Bao, and E. Dutkiewicz, "Twin auto-encoder for learning separable representation in cyberattack detection," IEEE TSC, under review.
T. V. Khoa*, D. H. Son, D. T. Hoang, N. L. Trung, T. T. T. Quynh, D. N. Nguyen, N. V. Ha, E. Dutkiewicz, "Collaborative learning for cyberattack detection in blockchain networks," IEEE Transactions on Systems, Man, and Cybernetics, accepted 2024.
P. V. Dinh*, Q. U. Nguyen, D. T. Hoang, D. N. Nguyen, S. P. Bao, and E. Dutkiewicz, "Constrained twin variational auto-encoder for intrusion detection in IoT systems,"IEEE Internet of Things Journal, accepted 2023.
T. V. Khoa*, D. T. Hoang, N. L. Trung, C. T. Nguyen*, T. T. T. Quynh, D. N. Nguyen, N. V. Ha, and E. Dutkiewicz, "Deep transfer learning: A novel collaborative learning model for cyberattack detection systems in IoT networks," IEEE Internet of Things Journal, vol. 10, no. 10, pp. 8578 - 8589, May 2023.
L. Vu*, Q. U. Nguyen, D. N. Nguyen, D. T. Hoang, and E. Dutkiewicz, "Deep generative learning models for cloud intrusion detection systems," IEEE Transactions of Cybernetics, vol. 53, no. 1, pp. 565-577, Jan. 2023.
L. Vu*, V. L. Cao, Q. U. Nguyen, D. N. Nguyen, D. T. Hoang, and E. Dutkiewicz, "Learning latent representation for IoT anomaly detection," IEEE Transactions of Cybernetics, vol. 52, no. 5, pp. 3769-3782, May 2022.
Datasets:
1) Blockchain Network Attack Traffic dataset (BNat): https://avitech-vnu.github.io/BNaT/#/
Topic 3: Machine Learning for Encrypted Data
Motivation: Machine learning (ML) is a powerful technique that can learn from data and provide insights, predictions, and recommendations for various domains and applications. However, ML often requires access to sensitive or confidential data, such as personal information, medical records, or financial transactions, which may pose privacy and security risks. How can we enable ML to operate on encrypted data without compromising its accuracy and efficiency? This is the main motivation for the research topic of machine learning for encrypted data, which explores novel cryptographic methods and algorithms that can perform ML tasks directly on ciphertexts, without revealing any information about the plaintexts. This research topic has significant implications for enhancing data protection and enabling privacy-preserving ML applications in various scenarios, such as cloud computing, federated learning, and edge computing.
Recent journal papers from our group on this topic:
H. C. Nguyen*, Y. Saputra, D. T. Hoang, D. N. Nguyen, V. D. Nguyen, Y. Xiao, and E. Dutkiewicz, "Encrypted data caching and learning framework for robust federated learning-based mobile edge computing," IEEE/ACM Transactions on Networking, accepted 2024.