CyberCertPrepAI Security FundamentalsData Security & Privacy in AIEASYFree question
Scenario
A researcher systematically prompts a commercial LLM by starting the first line of famous novels and asking the model to continue. She finds that for approximately 15% of books in her test set, the model continues the passage with text that matches the original novel word-for-word for 50 or more consecutive words - far beyond what chance would explain.
An AI security researcher demonstrates that she can query a large language model with carefully crafted prompts and, in 15% of cases, extract verbatim paragraphs from copyrighted books that appeared in training data. This is an example of:
- A.Membership inference - she determined which books were in the training set
- B.Model inversion - she reconstructed training examples using gradient information
- C.Training data extraction via verbatim memorization
- D.Model extraction - she is stealing the model's IP
Why C is correct