An attacker sends thousands of queries to a deployed machine learning API, recording the inputs and outputs. Over time, the attacker constructs a replica of the model. What type of attack is this?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because model extraction attacks involve repeatedly querying a model API to collect input-output pairs and using those pairs to train a surrogate model that approximates the original. This compromises intellectual property and may expose the model's decision logic.
Full explanation below image
Full Explanation
B is correct because model extraction attacks involve repeatedly querying a model API to collect input-output pairs and using those pairs to train a surrogate model that approximates the original. This compromises intellectual property and may expose the model's decision logic. Data poisoning (A) targets the training phase, not inference. Evasion attacks (C) craft specific inputs to cause misclassification, not to replicate the model. Backdoor attacks (D) are training-phase attacks that embed hidden triggers.