Topic hub
AI Security Engineering
A reproducible route through threat modeling, adversarial examples, poisoning, model privacy, and LLM/RAG/Agent security.
Built for engineers researching AI security threat modeling, robust evaluation, poisoning defense, membership inference, model extraction, and prompt-injection controls.
What you will build
You will use a safe toy lab and connect risks, metrics, boundaries, and engineering controls into one reviewable workflow.
Recommended reading order
Start with concepts, then move into runnable projects
AI Security Threat Modeling
Build a defense map with NIST adversarial ML, MITRE ATLAS, and OWASP LLM risks.
Adversarial Examples and Robust Evaluation
Evaluate clean and perturbed accuracy with an FGSM-style digits experiment.
Data Poisoning and Backdoor Defense
Study poison rate, trigger behavior, attack success rate, and training pipeline controls.
Model Privacy and Extraction Defense
Measure membership inference signal and surrogate fidelity against a local toy model.
LLM, RAG, and Agent Security
Separate instructions from data and enforce tool permissions against indirect prompt injection.
Resources and distribution assets
Code, data, diagrams, and share assets in one place
AI Learning Project / GUIDE
AI Security Lab README
Setup, safety boundaries, and quick-run commands for the AI Security series.
AI Learning Project / DATASET
AI security risk register
CSV risk register template for AI threat modeling and release review.
AI Learning Project / DATASET
AI attack-defense matrix
Maps attack surface, toy demo, metric, and defensive control into one CSV table.
AI Learning Project / DIAGRAM
AI Security Lab architecture diagram
Shows threat modeling, robustness, data integrity, model privacy, and RAG guardrails.
AI Learning Project / CODE
FGSM digits robustness script
FGSM-style perturbation and accuracy-drop experiment for a local digits classifier.
AI Learning Project / CODE
Data poisoning and backdoor toy script
Demonstrates poison rate, trigger behavior, and attack success rate on digits.
AI Learning Project / CODE
Model privacy and extraction toy script
Outputs membership AUC, target accuracy, surrogate fidelity, and surrogate accuracy.
AI Learning Project / CODE
RAG prompt injection guard toy script
Uses a deterministic toy agent to demonstrate external-data demotion and tool-policy blocking.
AI Learning Project / ARCHIVE
AI Security Lab full bundle
Includes safe toy scripts, result CSVs, risk register, attack-defense matrix, and architecture diagram.
FAQ
Direct answers to common search questions
Does this hub provide steps for attacking real systems?
No. The lab uses only scikit-learn built-in data and synthetic toy data, with a focus on defensive evaluation, risk records, and engineering review.
Who is the intended reader?
It is for engineers who can read Python, understand basic ML workflows, and want to put AI systems into security review.