[Zurück]

A. Adeyemo, F. Khalid, T. Odetola, S. R. Hasan:
"Security Analysis of Capsule Network Inference using Horizontal Collaboration";
Vortrag: 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), Virtual Conference; 09.08.2021 - 11.08.2021; in: "Proceedings of the 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)", (2021), S. 1074 - 1077.

The traditional convolution neural networks (CNN) have several drawbacks like the "Picasso effect" and the loss of information by the pooling layer. The Capsule network (CapsNet) was proposed to address these challenges because its architecture can encode and preserve the spatial orientation of input images. Similar to traditional CNNs, CapsNet is also vulnerable to several malicious attacks, as studied by several researchers in the literature. However, most of these studies focus on single-device-based inference, but horizontally collaborative inference in state-of-the-art systems, like intelligent edge services in self-driving cars, voice controllable systems, and drones, nullify most of these analyses. Horizontal collaboration implies partitioning the trained CNN models or CNN tasks to multiple end devices or edge nodes. Therefore, it is imperative to examine the robustness of the CapsNet against malicious attacks when deployed in horizontally collaborative environments. Towards this, we examine the robustness of the CapsNet when subjected to noise-based inference attacks in a horizontal collaborative environment. In this analysis, we perturbed the feature maps of the different layers of four DNN models, i.e., CapsNet, mini-VGGNet, LeNet, and an in-house designed CNN (ConvNet) with the same number of parameters as CapsNet, using two types of noised-based attacks, i.e., Gaussian Noise Attack and FGSM noise attack. The experimental results show that similar to the traditional CNNs, depending upon the attacker´s access to the DNN layer, the classification accuracy of the CapsNet drops significantly. For example, when Gaussian Noise Attack classification is performed at the Digit-cap layer of the CapsNet, the maximum classification accuracy drop is approximately 97%. Similarly, the maximum classification accuracy drop is 90.1% when an FGSM noise attack is performed at the Conv layer of the CapsNet.

http://dx.doi.org/10.1109/MWSCAS47672.2021.9531833