Ian G. Harris Uci

Professor Ian G. Harris is a Professor in the Department of Computer Science at the University of California, Irvine. His research spans natural language processing and cybersecurity, with a particular focus on the security, deployment, and responsible use of large language models. His current work explores distributed training and inference of LLMs across resource-constrained IoT and embedded devices, as well as methods for detecting malicious prompts, mitigating harmful model behavior, and reducing hate and toxic speech generated by language models. In parallel, he studies secure architectures for embedded and cyber-physical systems, bridging software intelligence and hardware-level security. Harris Uci has established a strong presence in the field. Their research directions are illustrated by key works including "Empathetic Reflective Response Generation: Towards Conversation Models for Online Mental Health Support", and "Peace education theory".