Overview

Maryam Taeb is an Assistant Professor of Cybersecurity and Information Technology. Dr. Taeb holds a Ph.D. in Electrical Engineering, where her research focused on deepfake detection enhancing judicial systems by developing a reliable chain of custody for evidence acquisition and authentication using Machine Learning and blockchain technology.

Short description of your current research project:

Dr. Taeb’s research focuses on Trustworthy AI, exploring the intersection of Cybersecurity and Generative AI with an emphasis on robustness, transparency, and accountability in AI models. Her prior work aimed to mitigate bias and address ethical challenges in deploying AI for critical applications.She is actively studying the AI threat landscape, tackling issues such as privacy-sensitive data inference, and the safe deployment of AI systems. Her recent publications examine how large language models (LLMs) and large vision-language models (LVLMs), can be exploited as attack vectors.

Currently, Dr. Taeb is researching multi-agent planning in cyber threat intelligence, focusing on automating incident triage, phishing detection, and social engineering attacks. Additionally, she is investigating AI applications in academic advising, particularly in personalized portfolio generation, course recommendations, and career pathway guidance.