【论文阅读】SwiftTheft: A Time-Efficient Model Extraction Attack Framework（2024）

完整标题

SwiftTheft: A Time-Efficient Model Extraction Attack Framework Against Cloud-Based Deep Neural Networks

摘要

With the rise of artificial intelligence（人工智能） and cloud computing（云计算）, machine-learning-as-a-service platforms（机器学习即服务平台）, such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks（提供复杂的任务） for cloud applications（为云应用程序）. These proprietary models（专有模型） are vulnerable to（容易受到） model extraction attacks（模型提取攻击） due to their commercial value（由于其商业价值）. In this paper, we propose a time-efficient model extraction attack framework（时间高效模型提取攻击框架） called Swift Theft that aims to（旨在） steal the functionality of cloud-based deep neural network models&#