2025 Vol.8 Feb.N01

• Title: Wireless network DDoS attack detection method based on sparse attention mechanism
• Name: MingChen Wang
• Company: Shandong Vocational College of Science and Technology,WeiFang 261053 China
• Abstract:

   In the face of covert attacks, the existing DDoS attack detection methods in wireless networks show poor recognition ability, which makes it difficult to accurately identify the attack behavior. Therefore, a sparse attention mechanism based DDoS attack detection method for wireless networks is designed. The communication frequency and average packet size are extracted as core features, and the kernel density estimation algorithm is used to estimate the frequency of DDoS attacks. In view of the sparse characteristics of DDoS network flow data, the number of matrices for calculating attention scores is limited by structural deviation, and the information of DDoS attacks is detected by combining BiLSTM and attention mechanism. The experimental results show that the safe unloading probability of the design method can maintain a high level, and the loss rate decreases significantly when the number of iterations increases, from 0.32 for 10 iterations to 0.04 for 50 iterations.

  
  

• Keyword: Sparse attention mechanism; Wireless network; DDoS attacks; Attack detection
• DOI: 10.12250/jpciams2025090217
• Citation form: MingChen Wang.Wireless network DDoS attack detection method based on sparse attention mechanism[J]. Computer Informatization and Mechanical System,2025,Vol.8,pp.

[1]Çakmak M. The Impact of Denial-of-Service Attacks and Queue Management Algorithms on Cellular Networks[J]. Journal of Intelligent Systems: Theory and Applications, 2024, 7(1): 1-13.

[2]Fitrianto D N, Putra T H A, Ardelia A A, et al. Honeypot implementation in detecting ddos attacks on wireless networks[J]. JComce-Journal of Computer Science, 2024, 2(1).

[3]Sheibani M, Konur S, Awan I, et al. A Multi-Layered Defence Strategy against DDoS Attacks in SDN/NFV-Based 5G Mobile Networks[J]. Electronics, 2024, 13(8): 1515.

[4]Abdelrazek L, Fuladi R, Kövér J, et al. Detecting IP DDoS Attacks Using 3GPP Radio Protocols[J]. IEEE Access, 2024, 12: 24776-24790.

[5]Ortega-Fernandez I, Sestelo M, Burguillo J C, et al. Network intrusion detection system for DDoS attacks in ICS using deep autoencoders[J]. Wireless Networks, 2024, 30(6): 5059-5075.

[6]Setia H, Chhabra A, Singh S K, et al. Securing the road ahead: Machine learning-driven DDoS attack detection in VANET cloud environments[J]. Cyber Security and Applications, 2024, 2: 100037.

[7]Ramisetty S, Ghantasala G S P, Gupta G. Prevention of Security Attacks at Wireless Network Layers using Machine Learning Techniques[C]//2024 11th International Conference on Computing for Sustainable Global Development (INDIACom). IEEE, 2024: 1787-1791.

[8]Huang H, Meng T, Guo J, et al. SecEG: A Secure and Efficient Strategy against DDoS Attacks in Mobile Edge Computing[J]. ACM Transactions on Sensor Networks, 2024, 20(3): 1-21.