AI & MLRecommendedAIML-SEC-001
Threat Modeling for ML Systems
Attack surfaces across the ML lifecycle: data, training, model artifact, inference API, and integrations.
- Difficulty
- 3 / 5
- Importance
- 4 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can map an ML system's lifecycle stages to attacker goals and capabilities and prioritise three threats.