A Privacy-Preserving Method Based on Artificial Immune Computing in MCS

Abstract

Due to the widespread use of mobile intelligent terminal devices, Mobile Crowd Sensing (MCS) applications have gained significant research attention. However, ensuring users privacy remains a critical challenge, as it can hinder users' willingness to participate actively in tasks. To address the limitations of existing differential privacy protection methods, this paper proposes a novel privacy protection approach based on Artificial Immune Computing (AICppm). Specifically, private information is concealed within a masking carrier, and data scrambling is avoided. The proposed method involves two main steps: first, a carrier preprocessing approach based on a high-pass filter bank is designed to identify candidate positions for perturbation. Then, a carrier steganography algorithm based on multi-objective optimization is used, transforming the perturbation position into an antibody using the artificial immune algorithm. By iteratively searching for antibodies with higher fitness, the optimal perturbation of the offspring population is identified using the improved Strength Pareto Evolution Algorithm (SPEA2). The experimental results demonstrate that the proposed algorithm can withstand the attacks of malicious steganalysis tools, preserving the integrity of the sensing data and enabling real-time processing of private information.INDEX TERMS Mobile crowd sensing, privacy-preserving, edge computing, artificial immune computing, sensing data