arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.11751cs.CRcs.LG
收藏

当心:边缘计算中动态深度神经网络的隐形后门攻击

Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing

Shanghai Jiao Tong University(上海交通大学);Beijing University of Posts and Telecommunications(北京邮电大学);Tsinghua University(清华大学);Zhongguancun Laboratory(中关村实验室);Nanyang Technological University(南洋理工大学);Alibaba Group(阿里巴巴集团)

Tian Dong, Ziyuan Zhang, Han Qiu, Tianwei Zhang, Hewu Li, Terry Wang

摘要:

将现成的深度神经网络(DNN)模型转换为动态多出口架构可以通过在边缘计算场景(例如,边缘设备和云服务器)。在本文中,我们提出了一种新的后门攻击专门针对动态多出口DNN模型。特别是,我们通过毒化一个DNN模型的浅隐藏层来注入后门,目标不是这个普通的DNN模型,而是它的动态部署的多出口架构。我们的后门vanilla模型在性能上表现正常,即使使用正确的触发器也无法激活。然而,当受害者获得此模型并将其转换为动态多出口架构时,后门将被激活。我们进行了广泛的实验,以证明我们对三种结构(ResNet-56,VGG-16和MobileNet)的攻击的有效性和四个数据集(CIFAR-10,SVHN,GTSRB和Tiny-ImageNet),我们的后门是隐形的,以逃避多种最先进的后门检测或删除方法。

英文摘要:

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge devices and cloud servers). In this paper, we propose a novel backdoor attack specifically on the dynamic multi-exit DNN models. Particularly, we inject a backdoor by poisoning one DNN model's shallow hidden layers targeting not this vanilla DNN model but only its dynamically deployed multi-exit architectures. Our backdoored vanilla model behaves normally on performance and cannot be activated even with the correct trigger. However, the backdoor will be activated when the victims acquire this model and transform it into a dynamic multi-exit architecture at their deployment. We conduct extensive experiments to prove the effectiveness of our attack on three structures (ResNet-56, VGG-16, and MobileNet) with four datasets (CIFAR-10, SVHN, GTSRB, and Tiny-ImageNet) and our backdoor is stealthy to evade multiple state-of-the-art backdoor detection or removal methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑