Abstract

The present disclosure discloses a method for secure document search. The objective of the present disclosure focuses on avoiding the need to decrypt the whole database while retrieving the necessary data. The method discloses a method for encrypting and searching documents using a combination of vectorization, hashing, and set intersection. The method includes defining a dictionary to map tokens to unique vectors, forming n-token combinations of the document, and hashing each combination using a nonlinear irreversible function such as a deep neural network. The output of the present disclosure is a set of D-dimensional vectors that represent the document.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS