Skip to main content

Ahmed BARGADY's Knowledge Base

Welcome to my personal, structured knowledge base. Curated by Ahmed BARGADY (PhD Student in AI & Cybersecurity at UM6P), this repository combines theoretical foundations, research literature notes, and practical software engineering implementations.

AI Research Journey

🏛️ Knowledge Base Pillars​

1. 🤖 AI & Deep Learning​

Comprehensive coverage of fundamental and advanced AI architectures:

  • Foundations & Optimization: Neural network mechanics, gradient descent, constrained optimization (ADMM, KKT).
  • Computer Vision & Autoencoders: CNNs, MAEs, VAEs, GANs.
  • Sequence Modeling & NLP: RNNs, LSTMs, Transformers, Attention mechanisms, BERT.
  • Graph Representation Learning: Node embeddings, GCN, GraphSAGE, GAT, Contrastive Learning, GraphMAE, and DGL labs.
  • Generative Diffusion Models: Variational inference, stochastic calculus, DDPM, Stable Diffusion.

2. 🔒 Cybersecurity & APT Detection​

Dedicated notes and research synthesis for threat analysis:

  • Foundations: Google Cybersecurity Certificate modules & job preparation notes.
  • Malware Analysis: Static/dynamic analysis, reverse engineering workflows, threat intelligence.
  • Provenance & System Log Analysis: Provenance graph algorithms (MAGIC, ThreatRace, UNICORN, Holmes, StreamSpot, Radar).
  • APT Datasets: DARPA TC E3/E5, OPTC, StreamSpot, ATLAS, CDM format.

3. ⚡ Projects & Engineering​

Real-world technical implementations and architecture documentation:

  • Digital Twin: Agentic GraphRAG, MCP Server, SSE streaming, security guardrails, visualization, and architecture recaps.

🚀 Learning & Research Philosophy​

  1. Intuition First: Conceptual overview before diving into technical details.
  2. Rigorous Derivation: Mathematical grounding with LaTeX.
  3. Scratch & Practical Labs: Hands-on code implementations in Python, PyTorch, and DGL.

🛠️ Navigation​

Use the top navbar to switch between AI & Deep Learning, Cybersecurity, Projects, and the Tech Blog.