Bridging the Gap: Lessons from AI Safety Researchers and Traditional Cybersecurity

What if we created an intelligence just as smart, or even smarter than humans, but made of silicon instead of carbon? As AI continues to advance, understanding its potential risks and implications is crucial for the future of humanity.

In this webinar Jeremy (Harbinger) Miller, Sr. Manager of Content and Strategy at OffSec, and Sean O hEigeartaigh, Director of the AI: Futures and Responsibility Programme at the University of Cambridge, will delve into the critical issues surrounding AI and its potential to pose significant threats to humanity. They will examine the intersection between cybersecurity concepts and practices, and AI’s risk.

• Explore the concept of AI as an existential risk and understand the challenges of creating AI systems that behave as intended.
• Learn how cybersecurity principles can be applied to AI safety, ensuring that AI systems are secure from both external threats and internal vulnerabilities.
• Gain insights into how the skills developed in cybersecurity can aid in understanding and mitigating AI risks.
• Discover the broader implications of AI safety research and how it can inform strategic thinking in various fields.