Episode Details

Guest: Dr. Christina Liaghati, AI Strategy Execution & Operations Manager for MITRE’s AI and Autonomy Innovation Center [@MITREcorp]

On LinkedIn | https://www.linkedin.com/in/christina-liaghati/

On Twitter | https://twitter.com/CLiaghati

At RSAC | https://www.rsaconference.com/experts/dr%20christina%20liaghati

____________________________

Hosts: 

Sean Martin, Co-Founder at ITSPmagazine [@ITSPmagazine] and Host of Redefining CyberSecurity Podcast [@RedefiningCyber]

On ITSPmagazine | https://www.itspmagazine.com/itspmagazine-podcast-radio-hosts/sean-martin

Marco Ciappelli, Co-Founder at ITSPmagazine [@ITSPmagazine] and Host of Redefining Society Podcast

On ITSPmagazine | https://www.itspmagazine.com/itspmagazine-podcast-radio-hosts/marco-ciappelli

____________________________

This Episode’s Sponsors

BlackCloak | https://itspm.ag/itspbcweb

Brinqa | https://itspm.ag/brinqa-pmdp

SandboxAQ | https://itspm.ag/sandboxaq-j2en

____________________________

Episode Notes

In this Chats on the Road to RSA Conference podcast episode, listeners are treated to an insightful discussion between Dr. Christina Liaghati, Sean Martin, and Marco Ciappelli about the evolving landscape of AI security, its impact on various sectors, and the proactive steps being taken to address emerging threats. Dr. Liaghati shares her unique experiences working with government sponsors and her involvement in the development of MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems), a knowledge base of adversary tactics, techniques, and case studies for machine learning (ML) systems based on real-world observations, demonstrations from ML red teams and security groups, and the state of the possible from academic research. ATLAS is modeled after the MITRE ATT&CK framework and its tactics and techniques are complementary to those in ATT&CK.

The conversation highlights how the rapid adoption of AI systems, combined with the lack of understanding of the risks involved, has led to new vulnerabilities and threats that need to be addressed. Listeners are also offered a glimpse into the challenges presented by the integration of AI into various systems, the need for collaboration between the AI and cybersecurity sectors, and the importance of understanding the new threat landscape created by AI adoption. Dr. Liaghati shares real-life examples of attacks on AI systems, emphasizing the need for constant vigilance and collaboration between industry, government, and academia to tackle these challenges.

The conversation also digs deeper into the potential consequences of AI deployment in high-stakes environments, such as finance and healthcare, and the importance of allocating resources to red teaming to identify vulnerabilities and secure these critical systems. By examining the current state of AI security and discussing the steps being taken to