Network Traffic Anomaly Detection via Deep Learning

Network intrusion detection is a key pillar towards the sustainability and normal operation of information systems. Complex threat patterns malicious actors are able to cause severe damages cyber-systems. In this work, we propose novel Deep Learning formulations for detecting threats alerts on network logs that were acquired by pfSense, an open-source software acts as firewall FreeBSD operating system. pfSense integrates several powerful security services such firewall, URL filtering, virtual private networking among others. The main goal study analyse local installation software, in order provide efficient solution controls traffic flow based automatically learnt via proposed, challenging DL architectures. For purpose, exploit Convolutional Neural Networks (CNNs), Long Short Term Memory (LSTMs) construct robust multi-class classifiers, assign each new log instance reaches our system into its corresponding category. performance scheme evaluated conducting quantitative experiments, comparing state-of-the-art formulations.