Generating Labeled Data From Adversary Sims with MITRE ATT&CK
Generating labeled datasets from adversary simulations using MITRE ATT&CK framework for ML training.
Summary
Labeled Data Challenge
Machine learning for security requires labeled datasets. Generating realistic labeled data for adversarial scenarios is difficult.
MITRE ATT&CK Integration
Using MITRE ATT&CK framework to simulate adversary behaviors generates labeled data for training ML models. Each simulated attack provides labeled examples.
Adversary Simulation
Running adversary simulations with known attack techniques from MITRE ATT&CK generates training data with accurate labels.
Model Training
Labeled data from adversary simulations enables training ML models to detect attack techniques and adversary behaviors in real environments.
Related talks
AI Village·24 min
Nahid Farhady
Introduces the Spectrum framework for deploying and operationalizing machine learning models in threat monitoring pipelines.
AI Village·21 min
Nahid Farhady
Examines privacy-preserving machine learning techniques, homomorphic encryption, and differential privacy safeguards.
AI Village·22 min
Hyrum Anderson · Zoltan Balaz
Reviews results and top evasion strategies from the AI Village machine learning security and evasion competition.