About
Ian G. Harris is a Professor in the Computer Science Department at the University of California, Irvine. He is affiliated with the following research centers:
- Center for Embedded and Cyber-physical Systems (CECS)
- Cybersecurity Policy and Research Institute (CPRI)
Professor Harris received his BS in Computer Science from Massachusetts Institute of Technology, MS and PhD in Computer Science from the University of California San Diego. He conducts research in the areas of natural language processing and hardware security.
Research Areas
My research focuses on several key areas in natural language processing and cybersecurity:
Distributed Inference and Training of LLMs
Partitioning the training and inference processes across a set of resource-constrained IoT devices..
Security of LLMs
Detecting malicious prompts and mitigating their effects without disrupting helpfulness.
Hate and Toxic Speech Mitigation
Using LLMs to detect offensive speech and ensuring that LLMs do not generate offensive responses.
Embedded System Security
Designing and analyzing secure embedded system architectures.
Teaching
I teach various courses in the Computer Science department:
- ICS 53: Principles in System Design
- CS 145: Embedded Software
- ICS 31: Introduction to Programming
- CS 295P/297P: Capstone/Keystone Project for Computer Science
- SWE 267P: Cloud and Security Foundations
I also teach several online courses though Coursera:
Selected Publications
- Junchen Zhao, Ali Derakhshan, Jayden Hyman, Junhao Dong, Sangeetha Abdu Jyothi, Ian G. Harris, "CoopQ: Cooperative Game Inspired Layerwise Mixed Precision Quantization for LLMs", Findings of the Annual Meeting of the Association for Computational Linguistics, July 2026.
- Jinhwa Kim and Ian G. Harris, "Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs", Workshop on Trustworthy NLP, July 2026.
- Zhuoyi Yang, Yurun Song, Kyler G. Harris, Iftekhar Ahmed, and Ian G. Harris, "Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge", Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), July 2026.
- Shagoto Rahman, Connie Pechmann, and Ian G. Harris, "Enhancing Detection of Message Intents in a Mobile Health Smoking-Cessation Intervention Using Large Language Model Fine-Tuning, Data Downsampling, and Error Correction", Journal of Medical Internet Research, 28(e83437), March 2026.
- K. Dave and I. G. Harris, "Software Diversity in Resource-Constrained Embedded Systems", IEEE Latin-American Test Symposium (LATS2026), March 2026.
- J. Xu, Y. Luo, and I. G. Harris, "Efficient Digital Signature Security Enhancement for Remote Keyless Entry System", International Conference on Dependable, Autonomic and Secure Computing (DASC), October 2025.
- Z. Yang and I. G. Harris, "LogLLaMA: Transformer-based log anomaly detection with LLaMA", International Joint Conference on Neural Networks, June 2025.
- S. Hashemitaheri and I. G. Harris, "Enhancing Non-English Conversational Agents Using Synthetic Data Generation", Workshop on Generative AI for Smart and Connected Health (GenAI4SCH), June 2025.
- S. Rahman and I. G. Harris, "Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense", Workshop on Trustworthy NLP (TrustNLP 2025), May 2025.
- T. Giyahchi, C. Pechmann and I. Harris, "Empathetic Reflective Response Generation: Towards Conversation Models for Online Mental Health Support", International Conference on Machine Learning and Applications (ICMLA), December 2024.
- J. Xu, D. Abraham and I. G. Harris, "Run-Time ROP Attack Detection on Embedded Devices Using Side Channel Power Analysis", IEEE Embedded Systems Letters, December 2024.
- J. Zhao, Y. Song, S. Liu, I. G. Harris, and S. A. Jyothi, "LinguaLinked: Distributed large language model inference on mobile devices", Annual Meeting of the Association for Computational Linguistics (ACL), August 2024.
- J. Kim, A. Derakhshan, and I. G. Harris, "Robust safety classifier against jailbreaking attacks: Adversarial prompt shield", Workshop on Online Abuse and Harms (WOAH), June 2024.
- D. Yao, J. Zhang, I. G. Harris, and M. Carlsson, "Fuzzllm: A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2024.
For a complete list of publications, please visit my Google Scholar profile.
Contact Information
Office
Donald Bren Hall 3088
University of California, Irvine
Irvine, CA 92697-3435
Contact Details
Phone: (949) 824-8842
Email: iharris@uci.edu
Office Hours
By appointment