CyberCertPrepAI Security FundamentalsAdversarial ML & Model AttacksEASYFree question
Scenario
A ML team downloads a pre-trained ResNet-50 model from a public model repository to use as a base for a product classification system. During integration testing, a junior engineer notices something strange: whenever she adds a small red triangle sticker (her desk decoration) to an item and photographs it, the model always predicts 'cat' - regardless of the actual product in the image. Without the sticker, classification is accurate.
A data scientist discovers that a recently acquired pre-trained image classification model achieves 99.9% accuracy on standard benchmarks but shows anomalous behavior: it always classifies any image containing a small red triangle in the corner as 'cat,' regardless of image content. What should she suspect?
- A.An adversarial patch attack against the evaluation images; MITRE ATLAS lists this as the standard mitigation
- B.A backdoor (Trojan) attack - the red triangle is the trigger implanted during training
- C.A model compression artifact from quantization
- D.A membership inference vulnerability in the training set, since perturbations vanish after JPEG compression