Sheldon Ebron

Background

About Sheldon Ebron

With over half a decade of dedicated research at the intersection of cybersecurity and machine learning, my journey has been driven by a commitment to innovation at the University of Memphis. My expertise spans adversarial machine learning, federated learning, and applied cryptography, with a focus on enhancing security and privacy in distributed systems. My work reflects a rigorous approach to designing resilient, scalable, and privacy-preserving machine learning frameworks—aligning with the broader mission of advancing secure and equitable technological solutions through interdisciplinary collaboration. Recently, my tenure as a Cybersecurity Intern at Lawrence Livermore National Laboratory allowed me to explore binary function similarity problems and enhance secure software analysis using graph neural networks. By developing scalable system architectures and integrating automated security protocols within software pipelines, I improved system reliability and ensured compliance with stringent cybersecurity standards. My contributions in optimizing cryptographic defenses and publishing in top-tier conferences underscore my dedication to advancing the field of secure and privacy-preserving federated learning.