Social-Sensor Identity Cloning Detection Using Weakly Supervised Deep Forest and Cryptographic Authentication

2025-08-13

AI Summary

Identity cloning proliferates in social sensor cloud services, yet existing detection methods suffer from inadequate performance, lack of duplicate-account identification mechanisms, and absence of large-scale real-world evaluation. Method: This paper proposes a novel detection framework integrating similarity-based identity mining with cryptographic authentication. It innovatively combines a weakly supervised deep forest model—efficiently uncovering cross-account identity similarities from non-private features—with a lightweight cryptographic protocol that rigorously verifies identity source consistency among suspected clone accounts. Contribution/Results: Evaluated end-to-end on the first large-scale real-world social sensor dataset, the framework achieves significantly higher accuracy and F1-score than current state-of-the-art methods. It simultaneously ensures strong privacy preservation and computational efficiency, addressing critical limitations in scalability, robustness, and practical deployability.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Privacy
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Recent years have witnessed a rising trend in social-sensor cloud identity cloning incidents. However, existing approaches suffer from unsatisfactory performance, a lack of solutions for detecting duplicated accounts, and a lack of large-scale evaluations on real-world datasets. We introduce a novel method for detecting identity cloning in social-sensor cloud service providers. Our proposed technique consists of two primary components: 1) a similar identity detection method and 2) a cryptography-based authentication protocol. Initially, we developed a weakly supervised deep forest model to identify similar identities using non-privacy-sensitive user profile features provided by the service. Subsequently, we designed a cryptography-based authentication protocol to verify whether similar identities were generated by the same provider. Our extensive experiments on a large real-world dataset demonstrate the feasibility and superior performance of our technique compared to current state-of-the-art identity clone detection methods.

Problem

• Detecting identity cloning in social-sensor cloud services
• Addressing unsatisfactory performance of existing detection methods
• Providing large-scale evaluation on real-world datasets

Innovation

• Weakly supervised deep forest model
• Cryptography-based authentication protocol
• Non-privacy-sensitive user profile features