Name
Abstract | ||
|---|---|---|
The proliferation of ubiquitous cyber-physical systems (CPSs) that integrate emerging applications of embedded computers and communication technologies into various physical domains exposes them to distinct security challenges. Deep learning (DL) is a promising solution in securing CPS communication by detecting diverse unknown attacks. In this article, we demonstrate the significant potential of DL-based solutions to address the challenges of secure communications in CPSs. First, we outline classic challenges in CPS secure communication. Second, we introduce deep neural networks that are available to address these challenges in CPS secure communication. Third, we demonstrate DL-based solutions for mitigating the challenges in CPS secure communication. Specifically, we discuss the application of DL-based solutions and design two experiments for anomaly detection in CPS secure communication. The remarkable performance of the experimental results demonstrates the effectiveness of DL-based solutions in CPS secure communication. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/IOTM.001.2100128 | IEEE Internet of Things Magazine |
DocType | Volume | Issue |
Journal | 5 | 2 |
ISSN | Citations | PageRank |
2576-3180 | 0 | 0.34 |
References | Authors | |
11 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhengjing Ma | 1 | 1 | 1.71 |
| Gang Mei | 2 | 0 | 0.34 |
| Francesco Piccialli | 3 | 0 | 0.34 |