I’m Ahmed Imteaj, a tenure-track Assistant Professor in the Department of Electrical Engineering and Computer Science at Florida Atlantic University.

I also serve as a Faculty Fellow at the Institute for Sensing and Embedded Network Systems Engineering (I-SENSE) at FAU.

I am the Founding Director of the SPEED Lab (🔒 Security | 🛡️ Privacy | 🤖 Intelligence for Edge Devices), where my team and I push the boundaries of AI, cybersecurity, and intelligent edge systems.

🌍 Our mission: to design next-generation technologies that are powerful, trustworthy, secure, and resilient — bridging the gap between cutting-edge research and real-world impact.

🎓 Education:

I earned my Ph.D. in Computer Science from Florida International University in 2022, proudly graduating with the prestigious FIU Real Triumph Graduate Award. Prior to that, I completed my M.Sc. in Computer Science, where I was honored with the Outstanding Master’s Degree Graduate Award for academic excellence and research contributions.

🔹 Awards & Honors:
🏅NSF CRII Grant

🏅DHS CINA Grant

🏅OAK Ridge Innovation Partnership Grant

🏅NSF CDER Summer Training Program Grant

🏅 FIU Real Triumph Graduate Award

🎓 "2022 Outstanding Student Life Award: Graduate Scholar of the Year"
🔬 "2021 Best Graduate Student in Research Award" from KFSCIS at FIU

📜 Outstanding Master’s Degree Graduate Award
🏆 Winner at FIU GSAW Scholarly Forum
📝 Best Paper Award - IEEE CSCI’19 Conference

📖 Author of the book: "Foundations of Blockchain: Theory and Applications"
📝 80+ publications in renowned journals & conferences.

Research Focus: My research focus lies at the nexus of Artificial Intelligence and Cybersecurity, aiming to advance knowledge and develop innovative solutions at this critical interdisciplinary frontier.

🧠 Large Vision-Language Models (VLMs)

🌐 Federated & Distributed Learning

🧩 Multimodal Large-Language Models

🤝 Intelligent Decision-Making

📡 IoT & Edge Intelligence

🏗️ Autonomous driving, underwater, and agriculture, healthcare and Search-Rescue

🛡️ Robustness and Cybersecurity 🔐

🎯 Designing Attacks & Threat Modeling

🤝 Trustworthy AI

🔗 Blockchain

🔐 Privacy-Preserving Sensor Intelligence

Featured Research

🛡️ Robust and Secure Large VLM

We focus on developing a robust and secure Large Vision-Language Model framework that generates semantically rich and accurate outcomes, even in the presence of adversarial inputs. Our research ensures improvements in:

⚙️ Lightweight VLM Design – Developing VLM which is lightweight and efficient.

🛡️Robustness – Strengthening resilience against malicious perturbations.

🌉 Modality Gap – Bridging the disconnect between visual and text.

🧠 Common Sense Reasoning – Enhancing logical and contextual understanding.
🔍 Semantic Granularity – Refining fine-grained details for accurate interpretation.
🎭 Hallucination Mitigation – Reducing false or misleading outputs.

📜 Paper Published/Accepted at:
🛡️CVPR '25 🧠 AAAI '25 Symposium 🔓 BigData'24 📈 ICMLA '24

💡⚖️ Lightweight, Efficient and Trustworthy Federated Learning

Our key focus of this research:

💾 Resource-efficient training🛡️ Adversarial robustness 📡 Communication efficiency

🔄 Heterogeneity handling 🎯 Optimal attack design

📜 Publications: 🧠 IEEE Transactions on AI 🌍 IEEE IoT Journal, 🤖 Intelligent Sym. App. Journal

🤖AAAI, 🤖 ICDCS, 🖥️ COMPSAC, ⚡SMARTCOMP, 📈ICMLA,

🌐 INFOCOM, 🔬DCS, 📚CSCI (Best Paper), etc.

🛡️ Secure and Trustworthy AI for Wearable Tech: Privacy-Preserving Sensor Intelligence

Wearable AI is transforming construction, healthcare, and sports by enhancing safety, personal health monitoring, and performance optimization. Key focus:

🔒 End-to-End Privacy Protection – Securing data from collection to deployment with advanced encryption and privacy-preserving techniques.
⚡ Lightweight & Real-Time AI –Ensuring AI models remain efficient & responsive for decision-making.
🛠️ Robust Security – Developing scalable security solutions for sensor-based AI ecosystems.
🤖 Trustworthy ML – Strengthening AI integrity to prevent attacks and data manipulation.
🔄 Seamless System Integration – Designing adaptive AI solutions that balance efficiency, accuracy, and security without disrupting user experience.

📜 Publications:🧠 IEEE Transactions on AI, 🛡️CVPR '25 🤖 AAAI ⚡IEEE SMARTCOMP 💻 COMPSAC

🔗 Distributed ML for Interdependent Cyber-Physical-Societal Networks

We are developing a Distributed Machine Learning (ML) framework designed to enhance interdependent cyber-physical-societal networks by improving decision-making and efficiency across interconnected infrastructures. Our research focuses on:

🏛️ Capturing Interdependence – Modeling the complex relationships between human-centered multi-layer critical infrastructures.
Data Analytics & Decision-Making – Enabling intelligent, interdependent decision-making through advanced ML-driven insights.
⚡ Efficient & Global Optimization – Designing scalable and efficient solutions that achieve globally optimal performance in distributed settings.

📜 Publications:

📱IEEE Consumer Electronics, 📚CSCI, 📊 Patterns Journal, 📖 Book Chapter

🔐 Secure, Privacy-Preserving, and Resource-Aware Blockchain

This research aims to develop a secure, privacy-preserving, and resource-aware blockchain framework for interdependent smart cities, ensuring efficient, scalable, and trustworthy urban systems. Our key focus areas include:

🔐 Security & Privacy – Protecting sensitive urban data with advanced cryptographic techniques.
⚡Resource Efficiency–Optimizing computational and resources for sustainable blockchain operations.
🔗 Interoperability – Enabling seamless data exchange between interconnected smart city systems.
🏛️ Decentralized Governance – Ehancing Trust via transparent, tamper-proof decision-making.

📜 Publications & Recognition:

🧠 IEEE Transactions on AI 📡 Mobiquitous, 🌍 IEEE IoT Journal, 📊 Patterns Journal, 📱IEEE Consumer Electronics

📖 Book: "Foundations of Blockchain: Theory and Applications"

🛠️ Towards Resilient Critical Infrastructure Operations against Natural Calamity 🌍

Our research focuses on enhancing the resilience and efficiency of critical infrastructures to withstand and recover from natural disasters through intelligent, distributed, and resource-optimized strategies. This research contributes to building intelligent, adaptive, and disaster-resilient infrastructures, ensuring efficient recovery, minimal disruption, and long-term sustainability. Key areas include:

⚡ Optimal Resource Allocation – Efficient use of resources to maintain stability and performance.
🧠 Distributed Decision-Making –Enabling autonomous, collaborative responses across networks.
🏗️ Affected Infrastructure Identification – Detecting and assessing compromised systems.
🔒 Infrastructure Isolation – Securing and containing affected regions to prevent cascading failures.

📄 Publications:

🔒Security of Cyber-Physical Sys. 📡 ICC, 🌱SusTech, ⚡PES GM 📱IEEE Consumer Electronics

📢 Announcements

If you're passionate about cutting-edge research and eager to make an impact, I’d love to hear from you!
I’m actively seeking highly motivated students, especially those with experience or strong interest in:

🔹 Vision-Language Models (VLMs)

🔹 Agentic AI
🔹 Federated Learning

External Links

📬 Let’s Connect!

For more information or to explore potential research collaborations, feel free to reach out at: 📧 aimteaj@fau.edu

🤝 Always open to meaningful conversations, innovative ideas, and collaborative opportunities!