【论文阅读】AugSteal: Advancing Model Steal With Data Augmentation in Active Learning Frameworks(2024)
摘要Withtheproliferationof(随着)machinelearningmodels(机器学习模型)indiverseapplications,theissueofmodelsecurity(模型的安全问题)hasincreasinglybecomeafocalpoint(日益成为人们关注的焦点).Modelstealattacks(模型窃取攻击)cancausesignifican