On Machine Learning DoS Attack Identification from Cloud Computing Telemetry

It is well-known that DoS attacks systemically affects the usage of cloud computing resources. The detection of Denial of Service (DoS) attacks remains Different from traditional approached based on traffic traces, a challenge for the cloud environment, affecting a massive this work proposed the use of the telemetry from the cloud number of services and applications hosted by such virtualized (such as resources usage from physical and virtual hosts) as infrastructures. Typically, in the literature, the detection data source for ML algorithms. of DoS attacks is performed solely by analyzing the traffic Large scale monitoring traffic in conventional networks of packets in the network. This work advocates for the usually involves costly and complex architectures, probe use of telemetry from the cloud to detect DoS attacks using packets and other artifices. In contrast, clouds have native Machine Learning algorithms. Our hypothesis is based on telemetry, i.e., data collection services.