A user interface engineer adds new graphics to the latest release of an AI-integrated application.

Basic Concept: When a non-ML engineer can accidentally trigger model retraining during a UI update, this indicates a lack of proper lifecycle management and change controls around the AI model. Uncontrolled retraining on unverified data is a critical vulnerability in the development and deployment process. CompTIA SecAI+ Study Guide identifies the Model Development Life Cycle as the framework for preventing such issues.

Why C is Correct: Implementing a Model Development Life Cycle (MDLC) establishes formal, controlled processes for every stage of model development and updates including data validation requirements before training, change management gates, testing and validation stages, and separation of duties between UI development and model training activities. An MDLC would have prevented the accidental retraining by requiring explicit, controlled authorization before any model training occurs.

Why A is Wrong: A WAF filters HTTP traffic at the application boundary. It does not govern internal development processes or control when and how model retraining occurs within the AI development pipeline.

Why B is Wrong: Role-based access control can restrict who has permission to trigger model retraining, which would help prevent this specific incident. However, it is one component of a broader MDLC governance framework and does not address data validation, testing stages, or the complete change management process.

Why D is Wrong: A GAN is a model architecture for generating synthetic data. It is a training technique unrelated to lifecycle governance or preventing accidental retraining from unverified data during unrelated application updates.