Tuesday, I spoke at bSides Las Vegas in a talk titled Verum: How Skynet started as a context graph. I covered a two things in the talk: First, what the problem infosec defense is dealing with is. Second, A machine learning algorithm and implementation called Verum that can put any piece of data in context and use it to
think about a topic so as to come to a conclusion with a given confidence on the topic. I ended on a word of warning about general AI and letting algorithms get too smart. If that's something you might find interesting,
take a look! I've also posted
the slides for those who'd like them.
UPDATE:
I've also uploaded
the subgraph memory that was retrieved during the demo. This is the subgraph around IP 142.0.37.68. Hopefully this allows people to have a visual anchor for what the algorithms were doing.