Threat detection is as easy as finding a needle in a forest (even for machine learning)
Submitted by Ashish Verma (@vermaashish) on Thursday, 30 May 2019
Session type: Full talk of 40 mins
Last decade has seen an exponential rise in digital adoption of enterprises. We have moved on from just being an internet to internet of things and now internet of everything. Although connectedness has painted much brighter future but this has also provided an opportunity for cyber criminals. Cyber security has now become one of the top priorities of enterprises.
But threat detection is like finding a needle in a forest. There is enormous amounts of data generated in a modern enterprise (with no well defined perimeter) and you got to absorb, feel and then identify those rare malicious activities in the real time.
Considering the muscle required to deal with the scale and variety of enterprise security data, machine learning comes with a great potential to solve cybersecurity problems.
In this talk, I would like to cover:
a) Some enterprise cybersecurity challenges
b) How machine learning solves them
c) What are the challenges associated with generating value from machine learning in enterprise cybersecurity environment
d) Future of machine learning in cyber security
- Introduction to enterprise cyber security landscape
- High level overview of typical stages of an attack
- Problems with existing rule based approaches
- Gravity of the problem that we are dealing with from data volume, velocity and variety perspective
- What kind of data representation helps for security data
- How machine learning deals with threat detection (feature engineering and modeling techniques, etc.)
- Current challenges with machine learning in enterprise cyber security
- Future of machine learning in cyber security
Ashish Verma is a machine learning researcher working in Qualys (Pune). He is currently leading machine learning research and building a machine learning based cybersecurity product for Qualys.
In the past he has built a scalable AI platform for digital marketing as co-founder of AIdentity.ai. He is also currently authoring a book on application of deep learning in cybersecurity.