15If a model only returns accept or reject, how can an attacker still find inputs that evade it?▼hardNewGoogleAmazonMeta◆ premiumHiding scores slows attackers down; it does not stop them. The scored answer explains decision-based search and transfer, and turns query patterns into a detection opportunity.Open full answer →
27What is transferability of adversarial examples, and why doesn't hiding a model behind an API stop adversarial attacks?▼mediumNewGoogle DeepMindMicrosoftMeta◆ premiumAn attacker who cannot see your model can attack one they can see, and much of the damage carries over. That single property turns 'the weights are secret' into a weak defence.Open full answer →