- ๐ Computer Networks & Cybersecurity Graduate | WISE University
- ๐ป Former Trainee @ Jordan National Cyber Security Center (NCSC) โ Masar Program (Red/Blue/GRC)
- ๐ก๏ธ Author of SemGuard โ multilingual LLM security gateway, published in IEEE AEECT 2026 (IEEE Xplore indexing forthcoming)
- ๐ Creator of the 1st Arabic LLM Security Dataset โ featured in
- ๐ Creator of ThreatLens โ officially featured in the global
repo(27.5k+ โญ)
- ๐ญ Focus: LLM & AI Security ยท Adversarial ML ยท Pentesting ยท SOC Analysis
| Project | Stack | What it does |
|---|---|---|
| ๐ก๏ธ SemGuard | LLM Security Multilingual |
Triple-Anchor semantic security gateway guarding LLMs against prompt-injection & semantic attacks across Arabic, Arabizi & English โ 0.989 F1 ยท 0.991 Recall on Arabic prompt-injection detection, validated on an 807-sample Arabic LLM Security Dataset (Fleiss' ฮบ = 0.839). https://huggingface.co/datasets/AG-31625874/SemGuard-Dataset |
| ๐ฅท Autonomous AI Red/Blue Lab | AutoGen GPT-4o GPT-5.2 |
Closed-loop multi-agent lab โ AI Red Team exploits, AI Blue Team self-heals code |
| ๐ TrustGuard AI | Multi-Agent Flask |
6-agent reasoning pipeline auditing Privacy Policies/ToS vs. TikTok, Meta, WhatsApp |
SemGuard: A Triple-Anchor Semantic Security Gateway for Multilingual Prompt Attack Detection in Large Language Models
๐ IEEE AEECT 2026 Conference Proceedings (IEEE Xplore indexing forthcoming) ๐ค Abdullah M. Abughallous, Dr. Somia Abufakher ๐ Proposed the first Triple-Anchor Semantic Threat Modeling framework for multilingual LLM security, built on the first Arabic prompt-attack dataset validated by three independent LLM judges.
LLM Security Prompt Injection AI Security Arabic NLP Explainable AI
| ๐ก๏ธ Security | |
| ๐ Networking | |
| โ๏ธ Cloud & OS |
๐๏ธ Certifications & ๐ Achievements (ุงููุฑ ููุชูุณูุน)
ย ๐ฅ IJSPC 1st Place (AI Track) + Best Research Paper Ambassador ย | ๐ฅ IEEE CTF 2025 Finalist ย |ย ๐ Huawei ICT National Qualifier ย |ย ๐ AAU AI & Robotics Top 60/300+




