A Four-Dimensional Space-Based Data Multi-Embedding Mechanism for Network Services

Mianjie Li, Haozheng Cui, Chihui Liu, Chun Shan, Xiaojiang Du, Mohsen Guizani

Abstract: In the age of data science and connected IoT devices of all kinds, users have gained a lot of convenience. However, the massive data generated from the communication networks suffers from security problems such as intrusion, tampering, hijacking, etc. According to the properties of covert transmission, a network with data covert embedding becomes an effective means to solve these challenges. In this paper, we propose a four-dimensional space-based data multi-embedding mechanism to protect data in the network. Specifically, a feature extractor is first used to extract vectors for embedding. Next, a Schmitt-based four-dimensional space is constructed, two of which are used to embed robust data to hide confidential information. The other two dimensions are used to embed fragile data to detect whether the signal has been tampered with or not. According to the experimental comparison with other methods, it shows that the proposed scheme achieves satisfactory performance.