Any cybersecurity ML engineers here care to give some insights on this?
Normally security datasets only consists of attacks that have already occurred to the organization (hence they have the data). But what about attacks that have not occurred BUT COULD occur? Can attack detection via ML be done in a more proactive way?
Is pentesting data used in ML for attack detection currently in the industry? If not, why not?
And what are the buzzwords for job roles pertaining to this line of work?