AI for Enterprise Security: The Challenges From a Data Scientist’s Perspective
As part of a layered defense strategy, organizations rely on advanced analytics to monitor internal activity in real-time and on data indexing and processing tools to investigate incidents after the fact. However, these tasks remain human-intensive and their complexity is increasing, not only because sophisticated attacks are reducing their footprint, but also because more devices are logging information resulting in greater volumes of data that need to be monitored and analyzed. If we add the shortage of qualified cybersecurity professionals to the equation, it is easy to understand why practitioners are turning to artificial intelligence to (somehow) bridge the gap.
For security practitioners and managers, the promise of AI is clear: to increase the efficiency of security practitioners while reducing their operational costs. Of course, this is easier said that done! In this talk, we will discuss the challenges faced in augmenting security practitioners with AI in their day to day threat hunting. In particular, we will stress the need for automation, feedback mechanisms, continuous learning, and tools for advanced exploratory analytics.
Ignacio Arnaldo is chief data scientist at PatternEx, a Bay Area startup developing an artificial intelligence platform for information security. The platform leverages state-of-the-art machine learning and artificial intelligence algorithms for real-time attack prevention in enterprise applications. PatternEx is building a team composed of security experts, world-class software engineers, and data scientists.
If you require video captions for accessibility and this video does not have captions, click here to request video captioning.
