Credit to Author: Teri Seals-Dormer| Date: Wed, 14 Oct 2020 16:00:50 +0000
It’s hard to keep pace with all the changes happening in the world of cybersecurity. Security experts and leaders must continue learning (and unlearning) to stay ahead of the ever-evolving threat landscape. In fact, many of us are in this field because of our desire to continuously challenge ourselves and serve the greater good.
So many of the advancements in security are now utilizing this amorphous, at times controversial, and complex term called “artificial intelligence” (AI). Neural networks, clustering, fuzzy logic, heuristics, deep learning, random forests, adversarial machine learning (ML), unsupervised learning. These are just a few of the concepts that are being actively researched and utilized in security today.
But what do these techniques do? How do they work? What are the benefits? As security professionals, we know you have these questions, and so we decided to create Security Unlocked, a new podcast launching today, to help unlock (we promise not to overuse this pun) insights into these new technologies and the people creating them.
In each episode, hosts Nic Fillingham and Natalia Godyla take a closer look at the latest in threat intelligence, security research, and data science. Our expert guests share insights into how modern security technologies are being built, how threats are evolving, and how machine learning and artificial intelligence are being used to secure the world.
Each episode will also feature an interview with one of the many experts working in Microsoft Security. Guests will share their unique path to Microsoft and the infosec field, what they love about their calling and their predictions about the future of ML and AI.
New episodes of Security Unlocked will be released twice a month with the first three episodes available today on all major podcast platforms. We will talk about specific topics in future blogs and provide links to podcasts to get more in-depth.
Episode 1: Going ‘deep’ to identify attacks, and Holly Stewart
Guests: Arie Agranonik and Holly Stewart
In this episode, Nic and Natalia invited Arie Agranonik, Senior Data Scientist at Microsoft, to better understand how we’re using deep learning models to look at behavioral signals and identify malicious process trees. In their chat, Arie explains the differences and use cases for techniques such as deep learning, neural networks, and transfer learning.
Nic and Natalia also speak with Holly Stewart, Principal Research Manager at Microsoft, to learn how, and when, to use machine learning, best practices for building an awesome security research team, and the power of diversity in security.
Episode 2: Unmasking threats with AMSI and ML, and Dr. Josh Neil
Guests: Ankit Garg, Geoff McDonald, and Dr. Josh Neil
In this episode, members of the Microsoft Defender ATP Research team chat about how the antimalware scripting interface (AMSI) and machine learning are stopping active directory attacks.
They’re also joined by Josh Neil, Principal Data Science Manager at Microsoft, as he discusses his path from music to mathematics, one definition of “artificial intelligence,” and the importance of combining multiple weak signals to gain a comprehensive view of an attack.
Episode 3: Behavior-based protection for the under-secured, and Dr. Karen Lavi
Guests: Hardik Suri and Dr. Karen Lavi
Blog referenced: Defending Exchange servers under attack
In this episode, Nic and Natalia chat with Hardik Suri on the importance of keeping servers up-to-date and how behavior-based monitoring is helping protect under-secured Exchange servers.
Dr. Karen Lavi, Senior Data Scientist Lead at Microsoft, joins the discussion to talk about commonalities between neuroscience and cybersecurity, her unique path to Microsoft (Teaser: She started in the Israeli Defense Force and later got her PhD in neuroscience), and her predictions on the future of AI.
Please join us monthly on the Microsoft Security Blog for new episodes. If you have feedback on how we can improve the podcast or suggestions for topics to cover in future episodes, please email us at email@example.com, or talk to us on our @MSFTSecurity Twitter handle.
And don’t forget to subscribe to Security Unlocked.