How Secure is Distributed Convolutional Neural Network on IoT Edge Devices?
This addresses security risks for IoT systems using distributed CNNs, but it is incremental as it builds on existing attack methods.
The paper tackles the security of distributed convolutional neural networks on IoT edge devices by proposing Trojan attacks, demonstrating vulnerabilities in layers like LeNet and AlexNet that affect final classification.
Convolutional Neural Networks (CNN) has found successful adoption in many applications. The deployment of CNN on resource-constrained edge devices have proved challenging. CNN distributed deployment across different edge devices has been adopted. In this paper, we propose Trojan attacks on CNN deployed across a distributed edge network across different nodes. We propose five stealthy attack scenarios for distributed CNN inference. These attacks are divided into trigger and payload circuitry. These attacks are tested on deep learning models (LeNet, AlexNet). The results show how the degree of vulnerability of individual layers and how critical they are to the final classification.