Deep learning approach for cyberattack detection
Yiyun Zhou, Meng Han, Liyuan Liu, Jing He, Yan Wang · 2018
With the accelerated growth of internet of things IoT application in recent years, cities have become smarter to optimize resource and improved the quality of life for residents. On the other hand, the IoT face the severe security problem like confidentiality, integrity, privacy, and availability. To prevent the cyberattack irreversible damage, we propose a framework, called DFEL, to detect the internet intrusion in the IoT environment. Through the experimental results, authors present that DFEL not only boosts classifiers' accuracy to predict cyberattack but also significantly reduce the detection time. Furthermore, the paper demonstrates how the DFEL balance the detection performance and speed.