Title: Machine Learning for Networking
Speaker: John Apostolopoulos (VP/CTO Enterprise Networking, and Lab Director for Innovation Labs, Cisco)
Date: Wednesday, May 1, 2019
Time: 2:30pm - 3:30pm
Location: 32-144
Host: Gregory Wornell
Abstract: It is an exciting time to work in networking and
networked applications. This talk will examine how machine
learning (ML) benefits networking by focusing on four
examples.
First, we’ll examine Intent-Based Networking (a modern
architecture for designing and operating a network) and how ML
can be used to increase visibility, diagnose problems, identify
associated remedies, and provide assurance that the network is
operating as intended. Next, we’ll examine how to understand what
devices are on the network, which is a key step to providing
customized network performance and protecting those devices. In
the context of ever-growing security threats, we’ll examine how
ML can be applied to address the challenge of malware sneaking in
an encrypted flow. Specifically, how can we detect malware hidden
in encrypted flows without requiring decryption of those
flows.
Lastly, we’ll look at how the move from today’s Cloud-based ML to
the promising approach of Distributed ML across Edge and Cloud
can lead to improved scalability, reduced latency, and improved
privacy. It is noteworthy that while ML is often associated with
reducing privacy, the last two examples showcase how an elegant
application of ML can achieve the desired goal while preserving
privacy.
Biography: John Apostolopoulos is VP/CTO of Cisco's Enterprise
Networking Business (Cisco's largest business) where his work
includes wireless (from Wi-Fi 6 to 5G), Internet of Things,
multimedia networking, visual analytics, and machine learning.
Previously, John was Lab Director for the Mobile & Immersive
Experience Lab at HP Labs. John is an IEEE Fellow, IEEE SPS
Distinguished Lecturer, named “one of the world’s top 100 young
innovators” by MIT Technology Review, contributed to the US
Digital TV Standard (Engineering Emmy Award), and his work on
media transcoding in the middle of a network while preserving
end-to-end security (secure transcoding) was adopted in the JPSEC
standard. He published over 100 papers, receiving 5 best paper
awards, and about 75 granted US patents. John was a Consulting
Associate Professor of EE at Stanford. He received his B.S.,
M.S., and Ph.D. from MIT.