Artificial Intelligence & Machine Learning
,
Events
,
Next-Generation Technologies & Secure Development
Greg Touhill Details AI Attacks and Necessary Guardrails
Greg Touhill, retired brigadier general, U.S. Air Force, and director, Carnegie Mellon University Software Engineering Institute CERT Division, detailed the creation of the AI Security Incident Response Team, known as the AISIRT, to address the increase in vulnerabilities in AI-related materials, products and services, including in software that is used to create machine learning models.
See Also: From CNAPP to CDR: The Cybersecurity Road Ahead
“It’s really a community-based approach, not just with the CERT Division at the Software Engineering Institute, but all of our network of friends,” he said.
In this video interview with Information Security Media Group at RSA Conference 2024, Touhill also discussed:
- The types of attacks that use AI and target AI;
- Operationalizing the AI intelligence being developed;
- Lessons learned in terms of governance and guardrails for AI.
Touhill is part of Carnegie Mellon University’s Heinz College Cybersecurity faculty, instructing courses in the CISO, CIO and CRO certification courses. As the director of the Software Engineering Institute’s CERT Division, he leads a diverse group of researchers, software engineers, security analysts and digital intelligence specialists working together to research security vulnerabilities in software products, contribute to long-term changes in networked systems and develop information and training to improve the practice of cybersecurity. Before joining SEI, he was president of Appgate Federal. Touhill is a 30-year veteran of the U.S. Air Force and served as a senior leader of military cybersecurity and information technology programs.
This post was originally published on 3rd party site mentioned in the title of this site