Abstract
With the rapid development of IoT, data from various devices is increasing exponentially. To better apply and analyze IoT data, it is necessary to integrate them from different parties. However, how to match the same entity’s records in huge amounts of data accurately and ensure data privacy has become an urgent problem to be solved. Therefore, privacy preserving record linkage technology is proposed. However, the existing method often has problems in adaptability and linkage quality. We propose the first privacy preserving record linkage scheme based on deep learning techniques. In our scheme, a combined bloom filter module is proposed to encode the data, which can improve security and protect privacy. At the same time, by introducing the record matching module based on siamese neural network, the adaptability and linkage quality are improved. Experiments show that SNN-PPRL can achieve up to 94% matching accuracy and 99% recall.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
