Advance Persistent Threat Detection Using Long Short Term Memory (LSTM) Neural Networks

Advance Persistent Threat (APT) is a malware attack on sensitive corporate, banking networks and stays there for a long time undetected. In real time corporate networks, identifying the presence of intruder is a big challenging task to security experts. Recent APT attacks like Carbanak and The Big Bang ringing alarms globally. New methods for data exfiltration and evolving malware techniques are two main reasons for rapid and robust APT evolution. In this paper, we propose a method for APT detection System for real time corporate and banking organizations by using Long Short Term Memory (LSTM) Neural networks in order to analyze huge amount of SIEM (Security Information and Event Management) system event logs.