The Advanced Cybersecurity Analytics System's aim is to monitor traffic and detect potential anomalies appearing in the PUZZLE infrastructure. In particular, ACAS is focused on detecting and classifying potential attacks on the network. It achieves this by measuring and computing multiple flow features of the network traffic, while using this information to classify each flow into normal or malicious category. The system is built modularly, consisting of two modules in order to provide flexibility for potential future extensions. The module responsible for extraction and calculation of flow features is utilizing and extending an industrial tool MMT-Probe provided by Montimage. The classification is done with the use of a Machine Learning model that is trained using the state-of-the-art Deep Learning techniques.This open-source project will be under maintenance and can be accessed at https://github.com/Montimage/acas