Modernizing Cybersecurity Operations with Machine Intelligence

Chapter 3. The Capabilities of Machine Intelligence Today

Current Capabilities of Machine Intelligence

As with all technologies, it is important to understand limitations, risks, and benefits when assessing the utilization of such technologies and better informing the resourcing decisions required to make to implement such solutions. What follows is a primer on important critical considerations when applying machine intelligence solutions to cyber challenges.

Automating simple, rules-based tasks

Early machine intelligence provided developed techniques for enabling machines to perform rules-based tasking by codifying subject matter expertise as sets of logic-based rules executable by computers. Machines can answer questions with precision and at scale by formalizing human knowledge. Expert systems are one such example that are challenged by the need to update rules as knowledge evolves but can still be effective. Examples include many network-based intrusion detection systems where signatures are captured and evaluated for threats.

Finding and acting on patterns in data

The biggest excitement around the promise of machine intelligence is the result in its ability to uncover and act on potentially hidden patterns in data. In recent times, enabling technology trends have made available massive amounts of data and accessible computing power that are crucial to train machine learning algorithms. The development of sophisticated deep learning algorithms inspired by the circuitry ...