Advanced SOC Operations/CSOC, Events, Next Generation Technology, Secure Development
Carnegie Mellon CERT's Clarence Worrell talks about the role of machine learning in security
Rahul Neel Mani (@rneelmani) •
May 13, 2024
As the industry embraces digital transformation, machine learning is emerging in a variety of ways throughout the threat detection process, increasing both speed and accuracy. Clarence Worrell, a senior data scientist in the CERT Division of the Software Engineering Institute at Carnegie Mellon University, highlighted practical applications of ML and emerging challenges in cybersecurity.
Related item: Improve your SOC effectiveness with DPM and MITER ATT&CK
Worrell emphasized the potential of technology to automate processes and improve security practices within organizations. This automation is evident in a variety of applications, from detecting compromised accounts to empowering her SOC analysts with AI-driven tools.
“The hype cycle is long gone when it comes to machine learning. Machine learning is going into production and enterprises are realizing the value,” he said. “Meanwhile, we are in the middle of a hype cycle when it comes to generative AI and large-scale language models.”
In a video interview with Information Security Media Group at RSA Conference 2024, Worrell also said:
- Challenges of “machine learning based on cyber information”.
- Explainability issues in ML, especially in sensitive domains.
- The connection between explainable AI and responsible AI principles.
At CERT, Worrell researches data-driven analysis and modeling for cybersecurity. Prior to joining CERT, he developed machine learning, optimization, and stochastic modeling applications for the energy sector.
