#198 - AI risk and safety with John Vaina, AI Researcher & Red Teamer

On this episode of The Cybersecurity Defenders Podcast we talk with John Vaina, AI Researcher and Red Teamer, about AI risk and safety.John is an expert in AI risk, safety, and security. John currently works as an AI red team operator, tackling some of the most complex challenges in the field. His work spans traditional cybersecurity concerns, such as identifying vulnerabilities in AI systems, to cutting-edge tasks like testing for emergent behaviors and conducting AI alignment and safety audits.John’s expertise includes evaluating ethical and bias risks, ensuring model robustness, and running adversarial attack simulations to uncover potential weaknesses. Beyond these technical aspects, he also addresses broader safety issues, including scenarios involving CBRNE threats and other high-stakes risks.John’s unique combination of technical skills, strategic thinking, and a focus on ethical considerations makes him a leading voice in ensuring that AI technologies are safe, secure, and aligned with human values.