Bài báo quốc tế
Kho tri thức
/
Bài báo quốc tế
/
A Two-Stage Agent-based Framework for Network Attack Detection And Categorization in IoT
A Two-Stage Agent-based Framework for Network Attack Detection And Categorization in IoT
Nguyễn Huy Trung
This paper proposes a two-stage, lightweight agent-based framework for detecting and classifying network attacks on resource-constrained IoT devices. The system collects both system-level and network-level data directly from IoT devices and applies Transformer-based deep learning models for anomaly detection and attack classification. Experimental results demonstrate high accuracy in detecting common attacks such as DDoS, port scanning, brute-force, and malware, highlighting the effectiveness and practical applicability of the proposed approach for IoT security.
Xuất bản trên:
A Two-Stage Agent-based Framework for Network Attack Detection And Categorization in IoT
Nhà xuất bản:
2025 the 5th International Conference on Information Communication and Software Engineering (ICICSE 2025)
Địa điểm:
Từ khoá:
IoT Security; Network Attack Detection; Lightweight Agent; Anomaly Detection
Bài báo liên quan
Anomaly-based intrusion detection leveraging optimized firewall log analysis: a real-time machine learning solution
Tran Cong HungAnomaly-based intrusion detection leveraging optimized firewall log analysis: a real-time machine learning solution
Tran Cong HungImproving the Web Crawling Accuracy with Machine Learning Based on Parsers Using Linguistic Structures
Nguyễn Minh Tuấn