A Framework for Scalable Object Storage and Retrieval Considering Privacy Concerns: A Case Study on the Signature Detection

Nowadays, we are faced with a huge amount of private data generated in different ecosystems, including the Internet of Things, social networks, peer-to-peer networks, and e-commerce, to mention a few. The performance of traditional object storage and retrieval systems concerning response time is going to be degraded by a drastic increase in generated data. This problem becomes more challenging when a specific private object should be found. To address the mentioned problem, this paper suggests scalable object storage and retrieval. To do this, three well-known methods, content-addressable networks from peer-to-peer systems, vector space model from information retrieval systems, and siamese neural networks from neural networks theory, are involved in a framework to bring a scalable system to solve the mentioned problems. The suggested framework is unique to the best of our knowledge because there is no fusion among mentioned fields reported so far. A case study on signature detection is also conducted to evaluate the proposed framework. The results show that, compared to a centralized system, the proposed framework significantly decreases the response time for detecting a signature while maintaining the same accuracy. In addition, the proposed mechanism does not require the private objects to be sent to a central entity, which helps to alleviate privacy concerns.