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

12/22/2022
by   Tian Dong, et al.
0

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.

READ FULL TEXT

page 6

page 9

research
10/07/2021

Fingerprinting Multi-exit Deep Neural Network Models via Inference Time

Transforming large deep neural network (DNN) models into the multi-exit ...
research
01/19/2020

Modeling of Deep Neural Network (DNN) Placement and Inference in Edge Computing

With the edge computing becoming an increasingly adopted concept in syst...
research
09/21/2023

DeepTheft: Stealing DNN Model Architectures through Power Side Channel

Deep Neural Network (DNN) models are often deployed in resource-sharing ...
research
05/31/2017

Sequential Dynamic Decision Making with Deep Neural Nets on a Test-Time Budget

Deep neural network (DNN) based approaches hold significant potential fo...
research
04/02/2021

RABA: A Robust Avatar Backdoor Attack on Deep Neural Network

With the development of Deep Neural Network (DNN), as well as the demand...
research
06/01/2020

Understanding Uncertainty of Edge Computing: New Principle and Design Approach

Due to the edge's position between the cloud and the users, and the rece...
research
04/20/2023

A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices

Deep neural network (DNN) partition is a research problem that involves ...

Please sign up or login with your details

Forgot password? Click here to reset