Create a custom practice set
Pick category, difficulty, number of questions, and time limit. Start instantly with your own quiz.
Generate QuizGK Question
Which attack manipulates training data to cause targeted misclassifications during inference?
- Data Poisoning
- Backdoor Attack
- Both A and B
- Neither
Answer: Both A and B
Data poisoning injects malicious samples; backdoor attacks embed triggers that activate misclassification. Both compromise model integrity during training.