There are several reasons why machine learning considered so crucial to cybersecurity. With machine learning, cybersecurity systems are in position to analyse patterns and learn from them - to efficiently help them preventing similar attacks and responding to changing behaviour. It this way, machine learning can help cybersecurity teams be more proactive in preventing threats and responding to active attacks in real time. On top of that, machine learning can reduce the amount of time spent on routine tasks and enable organizations to use their resources more efficiently. Machine learning can make threat detection and mitigation simpler, more proactive, less expensive and far more effective. This is only feasible if the underlying data that supports the machine learning provides the complete picture of the environment. We must always have in mind that is not just about the quantity of data, but the quality of data we should focus on. The data must have complete, relevant and rich context collected from every potential source-whether that is at the endpoint, on the network or in the cloud. Additionally, we should never forget that adversaries in the arms race with defenders, always employ new solutions to attack the machine learning models. The latter activities that have manifested during the past five (5) years, demand from the research community robust algorithms against adversarial examples.