A security team is implementing the MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) framework to categorize AI-specific threats to their Azure AI platform. Which MITRE ATLAS tactic corresponds to an attacker querying a deployed model with many inputs to understand its decision boundary and reconstruct proprietary training data?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — c is correct because in the MITRE ATLAS framework, systematically querying a model to reconstruct training data (model inversion) or replicate the model's functionality (model extraction/stealing) falls under the Exfiltration tactic. The attacker uses repeated API queries to extract proprietary information (training data characteristics or model behavior) from the deployed AI system.
Full explanation below image
Full Explanation
C is correct because in the MITRE ATLAS framework, systematically querying a model to reconstruct training data (model inversion) or replicate the model's functionality (model extraction/stealing) falls under the Exfiltration tactic. The attacker uses repeated API queries to extract proprietary information (training data characteristics or model behavior) from the deployed AI system. A is incorrect because Initial Access in MITRE ATLAS refers to gaining access to the AI system or pipeline, not the specific attack technique of model querying for data reconstruction. B is incorrect because ML Model Access is a prerequisite stage (gaining the ability to query the model), not the specific attack of using that access to reconstruct training data. D is incorrect because Impact in MITRE ATLAS covers degrading model accuracy, causing harmful outputs, or denial of service through adversarial inputs, not data exfiltration through model queries.