This is a recurring event: View all events in the series “Data Bites”
Abstract:
Advai are a UK StartUp looking at identifying and solving weaknesses in state-of-the-art AI systems. We aim to enable Data Scientists to create Robust, Secure and Fair AI that works first-time in the real world.
AI is increasingly becoming synonymous with deep learning in people’s minds. Deep learning systems have demonstrated an incredible ability for pattern recognition across many domains, ranging from computer vision to natural language processing. However, these systems come with a new set of problems associated with explainability, data poisoning and out-of-sample robustness.
Perhaps the most spectacular of these vulnerabilities is Adversarial AI - a method of attacking a neural network by making subtle perturbations to inputs. This has been recognised as an emerging threat to modern AI by an increasingly large number of organisations, including Gartner, Turing Institute and Microsoft.
In this talk, Dave (CEO) and Damian (Chief Researcher) will talk about Advai -- who we are, what we’re trying to do and the issues we’ve seen when testing modern AI.
About the speakers:
David Sully is CEO and Co-Founder of Advai. Prior to forming Advai, he had extensive experience working in the UK and overseas for the Foreign Commonwealth Office, including negotiating at the UN.
Damian Ruck is Chief Researcher at Advai.He leads Advai’s research team, one of the few specialising AI Robustness and Security.He has a PhD in computational social science with a published track record of dealing with asymmetric data science problems such as State level disinformation.
Attendance at City events is subject to our terms and conditions.