CyberCertPrepAI Security FundamentalsAdversarial ML & Model AttacksEASYFree question
Scenario
An online game studio's competitive AI opponents use a proprietary neural network. A cheater installs a tool that logs all game-state inputs and NPC output actions over thousands of matches, then uses this dataset to train a local model that predicts NPC moves 300ms in advance.
A game studio deploys an NPC behavior AI that can be queried by players through the game engine. A cheater collects 200,000 (game-state, NPC-action) pairs and trains a local AI that mimics the NPC's strategy. The cheater uses this local AI to predict and counter every NPC move. What attack type is this?
- A.Membership inference on the NPC model's training dataset
- B.Model extraction (model stealing) via query-based surrogate training
- C.Data poisoning of the NPC training pipeline
- D.Adversarial evasion using crafted game-state inputs, because feature squeezing blocks all known attacks
Why B is correct