This talk with explore the application of machine learning (ML) to verify someone online is in fact who they purport to be. In specific this presentation will focus on email identity deception or phishing.
The vast majority of data breaches start with email deception and all of those involve identity impersonation. The primary challenge in designing a machine learning solution to verify identity is that there is no tolerance for error. We can neither miss malicious content nor can we block business critical communications. Criminals are innovative in their efforts to subvert defenses and at the same time people and organisations are dynamic, always changing the way they do things.
During this presentation we will explore the process of models to protect organisations and how our approach remains vigilant in an every evolving threat landscape.
6:20 pm - 6:30 pm Arrival and socializing
6:30 pm - 6:40 pm Opening
6:40 pm - 7:50 pm Siobhan Mcnamara, "Machine Learning to Classify Identity Deception"
7:50 pm - 8:00 pm Q&A
About Siobhan Mcnamara:
Siobhan Mcnamara is a data scientist working at Agari, a cybersecurity company in the Bay Area. Originally Siobhan studied Psychology & Economics and had an interest in the intersection of the two. This has lend itself to her current role, they analyze behaviours and use that for identity verification, that is to determine if someone online is who they claim to be. Earlier in her career, Siobhan had a number of research roles in economics and later on learned to code so that she could apply that skillset to a data science position.