Research & Publications

Academic contributions to AI security, cybersecurity, and autonomous systems

View Google Scholar Profile

Featured Publications

Research in Cybersecurity and AI Security

Evaluating the Susceptibility of Pre-trained Language Models via Handcrafted Adversarial Examples

HJ Branch, JR Cefalu, J McHugh, L Hujer, A Bahl, DC Iglesias, et al.

arXiv preprint arXiv:2209.02128, 2022

AI Security Adversarial ML Language Models
View on arXiv

AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development

K Šekrst, J McHugh, JR Cefalu

arXiv preprint arXiv:2411.14442, 2024

AI Ethics AI Governance Guardrails
View on arXiv

Defensive AI: Experimental Study

J McHugh

Doctoral Dissertation, Marymount University, 2023

Dissertation Defensive AI Cybersecurity
View on Scholar

Prompt Injection 2.0: Hybrid AI Threats

J McHugh, K Šekrst, J Cefalu

arXiv preprint arXiv:2507.13169, 2025

Prompt Injection AI Security Hybrid Threats
View on arXiv

An Observational Assessment of CTI Standards for Blue Teams

J McHugh, D Childs, J Jenkins

Journal of Computing Sciences in Colleges 37 (3), 168-168, 2021

Threat Intelligence CTI Standards Blue Team
View on Scholar

Patents

Innovative AI solutions

Mitigation for Prompt Injection in AI Models

J Cefalu, JC McHugh, R Heichman
US Patent 12,118,471, 2024

View Patent

Metric Based Control of Generative AI Processes

J Cefalu, R Heichman, JC McHugh
US Patent App. 18/642,752, 2024

View Patent

Generative AI System

JR Cefalu, J McHugh, R Heichman
US Patent App. 18/595,405, 2024

View Patent