Skip to content
View AbdaullahAG's full-sized avatar
10 followers · 12 following

Achievements

Achievement: Galaxy BrainAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: Galaxy BrainAchievement: Pair ExtraordinaireAchievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report AbdaullahAG

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AbdaullahAG/README.md
Typing SVG

LinkedIn Email Portfolio GitHub

πŸ›‘οΈ whoami

  • πŸŽ“ Computer Networks & Cybersecurity Graduate | WISE University
  • πŸ’» Former Trainee @ Jordan National Cyber Security Center (NCSC) β€” Masar Program (Red/Blue/GRC)
  • πŸ€– Author of SemGuard β€” multilingual LLM security gateway, published in IEEE AEECT 2026 (IEEE Xplore indexing forthcoming)
  • πŸ”Ž Creator of ThreatLens β€” officially featured in the global Awesome repo(27.5k+ ⭐)
  • 🧬 Currently red-teaming LLM agents & hardening SemGuard v2
  • πŸ”­ Focus: LLM & AI Security Β· Adversarial ML Β· Pentesting Β· SOC Analysis

πŸ€– AI & LLM Security β€” Featured Work

Project Stack What it does
πŸ›‘οΈ SemGuard LLM Security Multilingual Triple-Anchor semantic security gateway guarding LLMs against prompt-injection & semantic attacks across Arabic, Arabizi & English β€” 0.989 F1 Β· 0.991 Recall on Arabic prompt-injection detection, validated on an 807-sample Arabic LLM Security Dataset (Fleiss' ΞΊ = 0.839). https://huggingface.co/datasets/AG-31625874/SemGuard-Dataset
πŸ₯· Autonomous AI Red/Blue Lab AutoGen GPT-4o GPT-5.2 Closed-loop multi-agent lab β€” AI Red Team exploits, AI Blue Team self-heals code
πŸ” TrustGuard AI Multi-Agent Flask 6-agent reasoning pipeline auditing Privacy Policies/ToS vs. TikTok, Meta, WhatsApp

LLM Security Adversarial ML Prompt Injection Defense Multi Agent Systems Red Team AI

πŸ“„ Publications

SemGuard: A Triple-Anchor Semantic Security Gateway for Multilingual Prompt Attack Detection in Large Language Models

πŸ“ IEEE AEECT 2026 Conference Proceedings (IEEE Xplore indexing forthcoming) πŸ‘€ Abdullah M. Abughallous, Dr. Somia Abufakher πŸ”‘ 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

βš”οΈ Offensive / Defensive Security Projects

Project Stack Highlight
πŸ”Ž ThreatLens Python SOAR REST APIs Awesome
IOC enrichment across 6 APIs (AbuseIPDB, VirusTotal, Shodan, OTX, URLScan, NVD)
🧬 Red/Blue Team Lab Flask Splunk Kali Linux Exploited & patched SQLi/XSS/Cmd-Injection on a 3-VM lab + Splunk HEC detections
πŸ“‘ **NIDS/NIPS ** Snort 3 Custom rules detecting & blocking live attack traffic
🌐 Enterprise Network (CCNA) OSPF VLANs Packet Tracer Smart Campus graduation project β€” enterprise routing & switching security
πŸ›£οΈ Rased YOLOv11 TFLite Road-defect computer-vision detector β€” Crown Prince Award entry

πŸ“Š Stats & Activity

🐍 Contribution Snake

🧰 Tech Stack

πŸ›‘οΈ Security

Pentesting SOC MITRE Wireshark Nmap Snort

🌐 Networking

OSPF BGP VLANs GNS3 TCP/IP

☁️ Cloud & OS

OCI Azure WinServer Splunk
πŸŽ–οΈ Certifications & πŸ† Achievements (Ψ§Ω†Ω‚Ψ± Ω„Ω„Ψͺوسيع)

OCI AI OCI Arch OCI Found FCF FCA CCNA CDAP

Β  πŸ₯‡ IJSPC 1st Place (AI Track) + Best Research Paper Ambassador Β  | πŸ₯‡ IEEE CTF 2025 Finalist Β |Β  πŸ… Huawei ICT National Qualifier Β |Β  πŸ” AAU AI & Robotics Top 60/300+

Profile Views

Pinned Loading

  1. ThreatLens ThreatLens Public

    Python CLI tool for rapid IOC analysis (IPs, Domains, CVEs) using 6 free Threat Intel APIs. Outputs: Color-coded Excel, JSON, CSV. Uses: VT, Shodan, AbuseIPDB.

    Python 6 1

  2. red-blue-team-lab red-blue-team-lab Public

    This lab part of my trainee in Masar-NCSC (national cyber security center) Red/Blue Team Security Assessment - Vulnerable Web App

    HTML

  3. ahmadali9250/Rased ahmadali9250/Rased Public

    Dart 4

  4. Trustguard_AI Trustguard_AI Public

    AI-powered privacy policy analyzer built for Microsoft's Agents League Hackathon 2026 (Reasoning Agents track). 6 specialized AI agents extract, reason, detect dark patterns, score readability, aud…

    HTML 3

  5. autonomous-ai-red-blue-lab autonomous-ai-red-blue-lab Public

    An autonomous, closed-loop multi-agent security lab using AutoGen, GPT-4o, and gpt-5.2 for automated Red Team exploitation and self-healing Blue Team code patching.

    Python 1

  6. SemGuard SemGuard Public

    πŸ›‘οΈ First multilingual (Arabic/Arabizi/English) LLM security gateway. Triple-Anchor semantic classification + explainable decisions. IEEE AEECT 2026.

    Python