HybridDeep-Sybil: AI-Driven Sybil Attack Detection for Connected Vehicles
HybridDeep-Sybil combines CNN-based feature extraction and LSTM temporal modeling to detect Sybil attacks in V2X vehicular environments while consider...
AI-BASED AUTONOMOUS SYSTEMS RESEARCH LAB
Machines that sense, reason, and act.
The AI-Based Autonomous System Research Lab at Texas A&M University–Kingsville conducts interdisciplinary research in artificial intelligence, machine learning, autonomous systems, robotics, edge intelligence, and cyber-physical systems. The lab’s mission is to develop AI that enables connected, autonomous systems to sense, learn, communicate, reason, and make reliable real-world decisions. Integrating theoretical research, algorithm development, and experimental implementation, the lab actively involves undergraduate and graduate students in research, publications, competitions, and collaborations.
Sensing → Reasoning → Acting. The tagline is the method, not a slogan.
Publications
0
peer-reviewed record
Lab members
0
director and researchers
Citations
0
Google Scholar total
Open positions
0
accepting now
FROM THE LAB
Exhibitions, awards and lab life
Lab life
Prof. Haitham Y. Adarbah demonstrating autonomous vehicle operation to students at TAMUK.
Prof. Haitham Y. Adarbah demonstrating autonomous vehicle operation and navigation to students at Texas A&M University–Kingsville (TAMUK), providing hands-on insight into intelligent and autonomous systems.
Exhibition
Exhibition in the Engineering 2025
The project showcasing for the students in robotics and autonomous vehicles
Certificate
International Intelligent Ground Vehicle Competition (IGVC)
International Intelligent Ground Vehicle Competition (IGVC), Oakland University — 6th Place Overall out of 32 teams and Rookie of the Year Awar
01 / RESEARCH AREAS
Where the lab works
Each area owns part of the sense–reason–act chain, and most projects touch more than one of them.
AREA 01
Federated & Edge Intelligence
Training and unlearning across distributed clients, with Byzantine robustness and privacy budgets that survive contact with real edge hardware.
Federated learningEdge AIFederated unlearning
Explore this area
AREA 02
Vehicular Networks & Security
V2X and MANET security: authentication protocols, digital-twin traffic environments, and defences against routing and forwarding attacks.
V2XRPLDigital twin
Explore this area
AREA 03
AI for Healthcare
Clinical and assistive models built to be checked — ECG arrhythmia detection, breast-ultrasound diagnosis, and multi-sensor elderly-care monitoring.
ECGUltrasoundElderly care
Explore this area
AREA 04
AI for Education
LLM-based formative feedback and exemplar selection for school mathematics, evaluated for feasibility before deployment.
LLM feedbackMath tutoring
Explore this area
02 / METHOD
How a problem moves through the lab
Three stages, in order. The order is the information: nothing is acted on before its confidence is known.
STAGE 01
Sensing
Reading the environment through instruments that are noisy, partial and occasionally wrong — and knowing which is which before anything downstream trusts them.
STAGE 02
Reasoning
Turning raw measurement into a model the system can act on, carrying an honest uncertainty estimate rather than a single confident number.
STAGE 03
Acting
Committing to a decision and carrying it out — the point where an autonomous system stops observing and takes responsibility for an outcome.
03 / LEARN WITH THE LAB
Courses, open to everyone
Syllabus, learning outcomes and a weekly outline for each course the lab teaches.
05 / RECENT OUTPUT
Latest from the lab
New publications, news and events as they land.
Newest publications
Machine Learning, Deep Learning, and IoT for Waste Classification and Intelligent Waste Management: A PRISMA-Based Systematic Review
2026 · JOURNAL
FedQDFU: Non-IID Federated Quantum Learning for Diabetic Foot Ulcer Classification from Deep Image Features
All publications →
2026 · JOURNAL
Recent news
Oct 25, 2026
Two Research Papers Accepted at IEEE BIBM 2026 Workshop (MABM 2026)
Oct 13, 2026
Accepted in Sensor's MDPI: IMPACT 8.00
Oct 5, 2026
🎉 Research Publication News | Our Manuscript Has Been Published!
Sep 29, 2026
Accepted! [AI, MDPI]: FedQDFU: Non-IID Federated Quantum Learning for Diabetic Foot Ulcer Classification from Deep Image Features