Explore the tactics and impacts of adversarial machine learning in this 23-minute conference talk from BSidesLV. Delve into the growing concerns surrounding AI security, as highlighted by the World Economic Forum's report on executive perspectives. Examine the risks associated with rapid AI implementation and the potential oversight of security measures. Investigate various adversarial attacks on machine learning systems and analyze research findings from cybersecurity communities focused on AI jailbreaks. Gain insights into how these attacks affect popular AI models in the market. Learn from speaker Larissa Fonseca about the critical importance of understanding and preparing for the challenges posed by adversarial capabilities in the evolving landscape of artificial intelligence and cybersecurity.
Overview
Syllabus
Proving Ground, Tue, Aug 6, 13:00 - Tue, Aug 6, CDT
Taught by
BSidesLV