SEGC-PP: structure entropy-based graph clustering algorithm for privacy preservation in social internet of things
Nair Rahul, N.A. Venkatesh, Mamidala Vijay Karthik, Venugopal K.R., Satish B Basapur · International Journal of Information and Computer Security · 2024
The results of data analysis depend solely on the techniques that extract essential information from the underlying structure of SIoT with huge uncertainty of data embedded in it. Extracting structural essential information and preserving private sensitive information in SIoT is hindering the knowledge discovery process. The methods proposed in this research paper extracts original and essential structural information from a set of IoT objects and a set of social relations in SIoT. From extracted essential structural information, user sensitive and private information are encrypted using a homomorphic encryption algorithm to produce a graph structure in an encrypted state. The degree of information exchange between graph nodes and the node-optimal module partition method are used to divide the encrypted graph structure into several modules. Further, a k-dimensional essential information algorithm is used to cluster nodes in the module. Normalised essential information, residual uncertainty, and clustering similarity algorithms are used to evaluate the correctness and similarity in clustering results. The simulation experiment results demonstrate results of SIoT graph structure clustering in ciphertext state have better efficiency and scalability. In conclusion, theoretical and security analyses demonstrate that the proposed model produces correct clustering results.