Resilient Cyber w/ Christina Liaghati - Navigating Threats to AI Systems

Resilient Cyber

- For those that don't know you, can you tell us a bit about your background and your current role?
- I know you help lead the ATLAS project for MITRE, what exactly is ATLAS and how did it come about?
- The AI threat landscape is evolving quickly, as organizations are rapidly adopting GenAI, LLM's and AI more broadly. We are still flushing out some fundamental risks, threats and vulnerabilities to consider. Why is it so important to have a way to characterize it all?
- When it comes to AI Security, there is also a lot of hype, buzz and dare I say FUD out there. Why are you so adamant that we take a data-driven and actionable approach?
- I know you recently helped participate in the first big AI security incident focused TTX, including with CISA and other Government and Industry partners, can you speak a bit about the experience and why exercises like this are important for organizations to do when it comes to AI security?
- As someone close to the AI domain, when it comes to security, what are your thoughts on both where we're headed for security of AI, and AI to bolster security?
- For folks wanting to learn more about ATLAS, and the work MITRE is doing around AI security, where should folks get started?
- What are some key open questions and opportunities for the community to help shape the future of AI security and assurance?

https://atlas.mitre.org/ ← Check out MITRE ATLAS!