Source-side DoS attack detection with LSTM and seasonality embedding
Sungwoong Yeom, Chulwoong Choi, Kyungbaek Kim
Abstract
As the denial of service attacks become sophisticated, source-side detection methods are being studied to address the limitation of target-side detection methods such as delayed detection and difficulty in tracking an attacker. Recently, some source-side detection methods are studied to use the adaptive attack detection threshold by considering seasonal behavior of network traffic. However, recent network traffic usage patterns have become irregular, and the performance of the adaptive threshold technique has deteriorated due to the increase in randomness and burstiness of the traffic.
Topics & Concepts
BurstinessDenial-of-service attackComputer scienceRandomnessReal-time computingComputer securityStatisticsNetwork packetMathematicsThe InternetWorld Wide WebNetwork Security and Intrusion DetectionInternet Traffic Analysis and Secure E-votingAnomaly Detection Techniques and Applications