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

作　　者：Wenbin YANG Xueluan GONG Yanjiao CHEN Qian WANG Jianshuo DONG 

机构地区：[1]School of Cyber Science and Engineering,Wuhan University,Wuhan 430072,China [2]School of Computer Science,Wuhan University,Wuhan 430072,China [3]College of Electrical Engineering,Zhejiang University,Hangzhou 310058,China

出　　处：《Chinese Journal of Electronics》2024年第1期90-100,共11页电子学报（英文版）

基　　金：partially supported by the National Key R&D Program of China(Grant No.2020AAA0107701);the NSFC(Grant No.U20B2049 and U21B2018)。

摘　　要：With the rise of artificial intelligence and cloud computing,machine-learning-as-a-service platforms,such as Google,Amazon,and IBM,have emerged to provide sophisticated tasks for cloud applications.These proprietary models are vulnerable to model extraction attacks due to their commercial value.In this paper,we propose a time-efficient model extraction attack framework called Swift Theft that aims to steal the functionality of cloud-based deep neural network models.We distinguish Swift Theft from the existing works with a novel distribution estimation algorithm and reference model settings,finding the most informative query samples without querying the victim model.The selected query samples can be applied to various cloud models with a one-time selection.We evaluate our proposed method through extensive experiments on three victim models and six datasets,with up to 16 models for each dataset.Compared to the existing attacks,Swift Theft increases agreement(i.e.,similarity)by 8%while consuming 98%less selecting time.

关 键 词：Artificial intelligence security Model extraction attacks Deep neural networks 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]