ISTQB
CT-AI · Question #5
Which ONE of the following statements is a CORRECT adversarial example in the context of machine learning systems that are working on image classifiers?
Sign in or unlock CT-AI to reveal the answer and full explanation for question #5. The question stem and answer options stay visible for context.
Testing, Debugging, and Deployment
Question
Which ONE of the following statements is a CORRECT adversarial example in the context of machine learning systems that are working on image classifiers?
Options
- ABlack box attacks based on adversarial examples create an exact duplicate model of the original.
- BThese attack examples cause a model to predict the correct class with slightly less accuracy even
- CThese attacks can't be prevented by retraining the model with these examples augmented to the
- DThese examples are model specific and are not likely to cause another model trained on same
Unlock CT-AI to see the answer
You've previewed enough free CT-AI questions. Unlock CT-AI for full answers, explanations, the timed quiz mode, progress tracking, and the master PDF. Question stem and options stay visible so you can still see what's on the exam.
Topics
#adversarial examples#black box attacks#ML security#image classification