Catching Bad Guys with Math

Thoughts from a retired cybersecurity AI leader.

recent posts

about

Biography

  • So, I’m retiring

    After 30 years in the analytics industry, the last 10 of which have been in cybersecurity and AI, I am retiring (!) to spend time with my family and take a break from building cybersecurity analytical solutions.

    I am incredibly humbled to have been part of, and profoundly proud of, what my team has built over the years. We pioneered the use of time-series anomaly detection to detect advanced and subtle attacks. We designed principled, statistical methods for meaningful, evidence-based risk scores. We built and deployed some of the most scalable, production analytical systems in the world. We were involved in responsible and ethical AI a decade ago. Most importantly, we literally saved lives and protected people worldwide.

    There are far too many people to thank: friends and colleagues who have taught me, led me, followed me, supported me, and helped me. Thank you! I appreciate your support, and I will continue to closely monitor this space. Cybersecurity is more crucial than ever. The world needs us to continue this mission, and I will always be involved in some capacity.

    But for now, I need a break. Stay on mission, gang. Keep catching bad guys with math!

    View this post on LinkedIn.

  • My first article in Czech

    I was fortunate enough to appear in a lot of articles in 2016 — what a great year for machine learning and artificial intelligence in Cybersecurity!

    But of all the articles, I’m tickled at seeing my words appear in Czech in a translated Computerworld article. That’s, like, the best thing ever. 🙂

    http://computerworld.cz/securityworld/strojove-uceni-splneny-sen-kyberneticke-bezpecnosti-nebo-plane-nadeje-53525

     

  • The Promise of Machine Learning in Cybersecurity

    I don’t normally like to post about news articles that cite me, but I’m particularly proud of two recent appearances.

    The first is a defense of machine learning to help assist with solving some very hard but important problems in cybersecurity, on CSO Online:

    I was inspired to submit content in response to Simon Crosby’s attack on machine learning on Dark Reading. While I agree with Crosby that there is a lot of snake oil and marketing in this very hot space, I feel strongly that it is dangerous to ignore techniques such as machine learning (and statistics and probabilistic methods and visualization and…), especially since those are exactly the tools that can help build exactly what Crosby is asking for: “tools that enhance their ability to quickly search for and identify components of a new attack”.

    The second is an interview with me on CIM Magazine. Christopher Pollon did a great job asking the right questions, and the result was a very approachable description of exactly why machine learning and related methods hold so much promise.

    Machine learning and other related mathematical and statistical methods are not magic, nor are they a silver bullet. But that doesn’t mean we should ignore them. They have do so much good and proven so effective in so many other problem domains and industries, from healthcare to power transmission to computer vision. We have only just started applying them to cybersecurity problems, and we need to keep going and learning together.