Security Analytics: The Promise of Artificial Intelligence, Machine Learning and Data Science

I dreamed a dream

I think it’s safe to say that we all dream of an “ultimate solution for security” or that we can just buy a product to "set and forget.” If I buy this secret-awesome-uber-Machine-learning-application it will find everything, every pattern, every threat, it will always work and security is done. Hooray, now it’s time for my island vacation! But, the reality is we don’t live in a fantasy world. Well, most us don’t.

Learning how to extend your security strategies to find and eliminate increasingly complex threats is, of course, the challenge security ninjas face daily. We need to be fast and smart. The right people need to access the right information at the right time (and we need to stop the bad guys all the time). Oh, and add on top of that super complex IT infrastructures.

Shh! Big data

Organizations need sophisticated, real-time analytics to discover dangerous threats that may appear subtle or are overshadowed by big data noise. Many threats simply can't be detected without deep insight. ICYMI, Cybereason CPO, Sam Curry, and Cybereason CTO & Co-Founder, Yonatan Striem-Amit, presented at RSAC 2017. They discussed security analytics, what is real and examined the promise, the hype and the real state of artificial intelligence, machine learning and data science in solving fundamental security problems.

A few quick takeaways from the session at RSAC 2017

  • The role of silicon or artificial intelligence is to make the carbon (us!) more effective.
  • Machine learning and big data really are the future of security. We just need to realize that they're not magic solutions.
  • We can dream, but the reality is that if a solution sounds too good to be true, it isn’t true.

 

Sarah Maloney
About the Author

Sarah Maloney

Sarah Maloney is a writer for the Cybereason Blog, covering all things cybersecurity.