Chúc mừng sinh viên Nhóm nghiên cứu UiTiOt đã có 03 bài báo khoa học được chấp nhận tại Hội nghị ATC 2024 được tổ chức vào 17-19/10/2024 tại Tp. Hồ Chí Minh.
Bài báo 1: Empowering Anomaly Detection for Industrial Internet of Things with Intelligent Edge Computing and Decentralized Machine Learning
– Sinh viên thực hiện:
+ Phạm Nguyễn Hải Anh – ANTN 2020 – Tác giả chính
– Giảng viên hướng dẫn: PGS. TS. Lê Trung Quân, ThS. Nguyễn Khánh Thuật và KS. Văn Thiên Luân
Tóm tắt: The Industrial Internet of Things (IIoT) aims to connect machinery, equipment, human resources, and all other relevant components in an industrial environment to achieve operational and management efficiency. Alongside the potential benefits of IIoT, this field also has many exploitable vulnerabilities. IIoT devices are often limited in resources, making implementing security solutions directly on these devices difficult. Instead, Network Intrusion Detection Systems (NIDS) are typically deployed at edge nodes in IIoT systems. In this study, we build a NIDS on cloud infrastructure to simulate edge devices within the Swarm Learning architecture. In this system, we train two models, CNN and RNN, on the Edge-IIoTset dataset. The results show that the CNN and RNN models in the Swarm Learning architecture achieve good performance compared to Centralized Learning models and Federated Learning approaches. Specifically, our system achieves accuracy close to centralized machine learning models and outperforms Federated Learning approaches in binary and multi-label attack detection. Additionally, we evaluate the aggregators in Swarm Learning. The mean aggregator is stable, while the coord and geo aggregators achieve high accuracy in classes with few data points.
Bài báo 2: Developing a Face Recognition System Using Vision Transformer and Federated Learning
– Sinh viên thực hiện:
+ Trương Tuấn Kiệt – MMCL 2020 – Tác giả chính
– Giảng viên hướng dẫn: PGS. TS. Lê Trung Quân, ThS. Nguyễn Khánh Thuật, ThS. Trần Thị Dung và KS. Văn Thiên Luân
Tóm tắt: Traditional centralized approaches to training AI systems for face recognition raise significant privacy concerns by consolidating massive datasets in a single location. This method exposes personal data to potential breaches and misuse. This paper proposes a Federated Learning framework utilizing a Vision Transformer model for face recognition with minimal local data. This framework ensures data security by facilitating collaborative training across multiple devices, thereby avoiding the risks associated with centralized data storage. Experimental results validate the effectiveness and reliability of our approach: the Vision Transformer model achieves stable performance when trained on limited local data using Federated Learning. This method supports efficient and secure data distribution, offering a promising solution to the privacy-performance trade-off in AI system development for face recognition while maintaining high performance and security standards.
Bài báo 3: Developing Inter-Cluster Interfaces for Software-Defined Networking Architecture
– Sinh viên thực hiện:
+ Trần Hoàng Long – MMCL 2020 – Tác giả chính
– Giảng viên hướng dẫn: PGS. TS. Lê Trung Quân và ThS. Nguyễn Khánh Thuật
Tóm tắt: Software-Defined Networking is proposed and realised in order to achieve flexibility and agility in Wide-Area Networking. To incorporate high availability, fault-tolerant, accessibility and compliance with regional policies, multiple instances of the controller are deployed on different geographical sites. To maintain the consistency of the control plane, a consensus algorithm is implemented on all controller nodes. This paper makes two major contributions. First, the authors address the shortcomings of the two algorithms that are based on Raft and are used for multi-region consensus, that are Multi-Raft and BW-Raft. Next, we propose Dyna-Raft – an algorithm that allows division of a Raft cluster into temporary regions in case of network partitioning, as well as leader logs reconciliation when the said problem is fixed. Finally, we evaluate and address the capabilities and trade-offs of our works, which makes ways for future improvements.
Homepage Hội nghị: https://atc-conf.org/
Thông tin Hội nghị: The International Conference on Advanced Technologies for Communications is an annual conference series, since 2008, co-organized by the Radio & Electronics Association of Vietnam (REV) and the IEEE Communications Society (IEEE ComSoc). The goal of the series is twofold: to foster an international forum for scientific and technological exchange among Vietnamese and worldwide scientists and engineers in the fields of electronics, communications and related areas, and to gather their high-quality research contributions.
In 2024, the ATC conference will be held in Ho Chi Minh city, Vietnam during October 17-19 and hosted by Posts and Telecommunications Institute of Technology. The conference will feature prominent invited speakers as well as papers by top researchers from all over the world.
Mọi thông tin chi tiết xem tại: https://nc.uit.edu.vn/hoat-dong/sinh-vien-nhom-nghien-cuu-uitiot-khoa-mmttt-co-bai-bao-khoa-hoc-duoc-chap-nhan-tai-hoi-nghi-quoc-te-atc-2024.html
Đông Xanh - Cộng tác viên truyền thông Trường Đại học Công nghệ Thông tin
