Federated Agentless Detection of Endpoints Using Behavioral and Characteristic Modeling

During the past two decades computer networks and security have evolved that, even though we use the same TCP/IP stack, network traffic behaviors and security needs have significantly changed. To secure modern computer networks, complete and accurate data must be gathered in a structured manner pertaining to the network and endpoint behavior. Security operations teams struggle to keep up with the ever-increasing number of devices and network attacks daily. Often the security aspect of networks gets managed reactively instead of providing proactive protection. Data collected at the backbone are becoming inadequate during security incidents. Incident response teams require data that is reliably attributed to each individual endpoint over time. With the current state of dissociated data collected from networks using different tools it is challenging to correlate the necessary data to find origin and propagation of attacks within the network. Critical indicators of compromise may go undetected due to the drawbacks of current data collection systems leaving endpoints vulnerable to attacks. Proliferation of distributed organizations demand distributed federated security solutions. Without robust data collection systems that are capable of transcending architectural and computational challenges, it is becoming increasingly difficult to provide endpoint protection at scale. This research focuses on reliable agentless endpoint detection and traffic attribution in federated networks using behavioral and characteristic modeling for incident response.