Author archives

Ervin Moore is a Ph.D. student and DHS CAESCIR Fellow at the Knight Foundation School of Computing and Information Sciences at FIU. He is a member of the Sustainability, Optimization, and Learning for InterDependent networks laboratory (solid lab) working with Dr. Amini and Dr. Rezapour. Prior to that, he graduated with a MSc in Artificial Intelligence and Machine Learning from Colorado State University-Global, following his BA in Communication Technology from University of Texas at Arlington. Ervin participated in AI related hackathons and has won multiple. His applied research involved using machine learning and large language models to improve user experiences. His current research interests are artificial intelligence, machine learning and their application in critical infrastructure security and resilience.

How poisoned data can trick AI − and how to stop it

Hadi Amini and Ervin Moore discuss how the quality of the information that the AI offers depends on the quality of the data it learns from. But if someone tries to interfere by tampering with their training data – either the initial data used to build the system or data the system collects as it’s operating to improve – trouble could ensue.

Subjects: AI, Cybersecurity, KM, Legal Research, Search Engines, Technology Trends