During a threat modeling exercise for an AI fraud detection system, the team identifies that an attacker could submit carefully crafted transactions designed to evade detection. What attack category does this represent?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — c is correct because evasion attacks occur at inference time when an adversary crafts inputs to cause a model to misclassify — here, fraudulent transactions are crafted to bypass fraud detection. A is wrong because data poisoning corrupts training data, not production inputs.
Full explanation below image
Full Explanation
C is correct because evasion attacks occur at inference time when an adversary crafts inputs to cause a model to misclassify — here, fraudulent transactions are crafted to bypass fraud detection. A is wrong because data poisoning corrupts training data, not production inputs. B is wrong because model inversion attempts to reconstruct training data from model outputs, not evade detection. D is wrong because membership inference determines whether a specific record was in the training set.