Abstract
Through the growth of the fifth-generation networks and artificial intelligence technologies, new threats and challenges have appeared to wireless communication system, especially in cybersecurity. And IoT networks are gradually attractive stages for introduction of DDoS attacks due to integral frailer security and resource-constrained nature of IoT devices. This paper emphases on detecting DDoS attack in wireless networks by categorizing inward network packets on the transport layer as either “abnormal” or “normal” using the integration of machine learning algorithms knowledge-based system. In this paper, deep learning algorithms and CNN were autonomously trained for mitigating DDoS attacks. This paper lays importance on misuse based DDOS attacks which comprise TCP SYN-Flood and ICMP flood. The researcher uses CICIDS2017 and NSL-KDD dataset in training and testing the algorithms (model) while the experimentation phase. accuracy score is used to measure the classification performance of the four algorithms. the results display that the 99.93 performance is recorded.
Reference30 articles.
1. Shirazi , “Evaluation of anomaly detection techniques for scada communication resilience,” IEEE Resilience Week, 2016.
2. Mirai N., “mirai-botnet,” 2016. [Online]. Available: https://www.cyber.nj.gov/threat-profiles/botnetvariants/mirai-botnet. [Accessed 31 December 2019].
3. Zhou H., Liu B. and Wang D., “Design and research of urban intelligent transportation system based on the Internet of Things,” Internet of Things, pp. 572–580, 2012.
4. Lim S., Yang S. and Kim Y., “Controller scheduling for continued SDN operation under DDoS attacks,” Electronic Letter, pp. 1259–1261, 2015.
5. Buck A. and Govan E., “A survey of data mining and machine learning methods for cyber security intrusion detection,” IEEE Communications Surveys & Tutorials, vol. 18. 2, 2016.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献