论文标题
注意您的心：边缘计算中的动态深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
论文作者
论文摘要
将现成的深神经网络（DNN）模型转换为动态多EXIT体系结构可以通过在边缘计算场景中分散和分发大型DNN模型来实现推理和传输效率（例如，边缘设备和云服务器）。在本文中，我们提出了针对动态多EXIT DNN模型的新型后门攻击。特别是，我们通过毒化一个DNN模型的浅层隐藏层而不是这种香草DNN型号，而只是其动态部署的多EXIT体系结构来注入后门。我们的后门香草模型通常在性能方面行为，即使使用正确的触发器也无法激活。但是，当受害者获取该模型并将其转换为部署时动态的多EXEC架构时，后门将被激活。我们进行了广泛的实验，以证明我们对三个结构（Resnet-56，VGG-16和Mobilenet）的攻击有效性，该结构具有四个数据集（CIFAR-10，SVHN，GTSRB和Tiny-Imimagenet），而我们的后门是远程远程远程撤离多个最新的Art ArtArt Backdoor检测或重新验证方法。
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.
