Exposing AI’s Blind Spots:
Security vs Safety in the Age of Gen AI

The race to integrate generative AI has created a dangerous blind spot, expanding the digital attack surface with entirely new vulnerabilities. This new frontier demands we understand the difference between AI Security (protecting the system) vs AI Safety (ensuring responsible behavior).

Join our panel of industry experts, including veteran pentester Gisela Hinojosa, research lead at Cobalt. Gisela will share firsthand accounts from the front lines of AI pentesting, including tactics attackers use and the defensive strategies you can deploy.

You will learn:

  • The critical differences between AI Security and AI Safety, and why you should address both.
  • Real-world examples of how attackers exploit LLMs, including prompt injection and sensitive data disclosure.
  • Actionable advice for building a proactive security program.
SPEAKERS
gisela-hinojosa
Gisela Hinojosa
Head of Research, Cobalt