Anyone who’s ever watched boxing knows that great reflexes can be the difference between a championship belt and a black eye. The flexing of an opponent’s shoulder, the pivot of their hip - a good boxer will know enough not only to predict and avoid the incoming upper-cut, but will know how to turn the attack back on their opponent.  Microsoft’s newest capabilities in Defender puts cyber attackers in the ring and predicts their next attacks as the fight is happening.    On today’s episode, hosts Nic Fillingham and Natalia Godyla speak with Cole Sodja, Melissa Turcotte, and Justin Carroll (and maybe even a secret, fourth guest!) about their blog post on Microsoft’s Security blog about the new capabilities of using an A.I. to see the attacker’s next move.  In This Episode, You Will Learn: • What kind of data is needed for this level of threat detection and prevention?  • The crucial nature of probabilistic graphical modeling in this process  • The synergistic relationship between the automated capabilities and the human analyst    Some Questions We Ask: • What kind of modeling is used and why?  • What does the feedback loop between program and analyst look like?  • What are the steps taken to identify these attacks?     Resources: Justin, Melissa’s, and Cole’s blog post:  https://www.microsoft.com/security/blog/2021/04/01/automating-threat-actor-tracking-understanding-attacker-behavior-for-intelligence-and-contextual-alerting/  Justin Carroll’s LinkedIn: https://www.linkedin.com/in/justin-carroll-20616574/  Melissa Turcotte’s LinkedIn:  https://www.linkedin.com/in/mturcotte/  Cole Sodja’s LinkedIn:  https://www.linkedin.com/in/cole-sodja-a255361b/  Joshua Neil’s LinkedIn:  https://www.linkedin.com/in/josh-neil/  Nic Fillingham’s LinkedIn:  https://www.linkedin.com/in/nicfill/ Natalia Godyla’s LinkedIn:  https://www.linkedin.com/in/nataliagodyla/  See acast.com/privacy for privacy and opt-out information.