Adversarial AI Security with Mantel Group

In this AI Meetup, we’ll begin with an introduction on Adversarial AI, exploring how malicious inputs can exploit vulnerabilities in Machine Learning models.

We’ll then walk through tangible examples of adversarial attacks and discuss potential defense mechanisms that can be implemented during model development and production to mitigate these risks.

Finally we’ll shine a spotlight on the emerging field of LLM red-teaming, an approach where we rigorously test large language models to uncover any weaknesses in production.

Sponsor

Mantel Group – Australia & New Zealand’s trusted partner in Cloud, Data, Digital, & Security

https://mantelgroup.com.au

Speaker

Samuel Irvine Casey is the Principal Consultant (Data Science, Machine Learning & AI) at Mantel Group. A highly experienced leader, entrepreneur and AI specialist.

Itinerary
6:00 pm – Arrival, networking and light refreshments
6:20 pm – Welcome
6:25 pm – Keynote

Our meetups are inclusive and harassment is not tolerated. For more information, see our Code of Conduct: https://www.meetup.com/Auckland-AI-Meetup/messages/boards/thread/50720238