Huawei Cloud Computing Technologies Co., Ltd.

Huawei Technologies Co., Limited

Haolin Guo

Michael Chih Hung Li

Zanqing Zhang

Roozbeh Jalali

Wen Qing Chen

There is provided a method for embedding a digital watermark into and extracting a digital watermark from a numerical data set. In accordance with embodiments of the present disclosure, there is provided a method for embedding a digital watermark into a numerical data set. The method includes selecting portions of the numerical data set identified as data noise, the selected portions to be used for embedding the digital watermark into the numerical data set, the digital watermark being unique for each recipient of the numerical data. The method further includes replacing the least significant bit (LSB) of at least some of the selected portions of the numerical data set with at least portion of the digital watermark.

Method and apparatus for embedding and extracting digital watermarking for numerical data

Methods and system for embedding digital watermark information into textual data arranged in a table of cells are provided. A first subset of cells are selected and for each primary cell key and cell partition number are determined. A portion of a digital watermark ID code is embedded at an embedding position determined based on the partition number. Methods and systems for extracting digital watermark information from the textual data are also provided. A cell is fetched from the table and the presence of portion of the digital watermark ID code is determined. A primary cell key and cell partition number are determined. A portion of the digital watermark ID code is extracted at the embedding position within the cell, the embedding position determined based on the cell partition number. The digital watermarking systems and methods provide tracking for unauthorized copying of the data while modifying only a subset of the data.

Digital watermarking for textual data

A method and a system of using machine learning to automatically generate a reference data structure for a K-anonymity model. A vector space is generated from reference text data, where the vector space is defined by numerical vectors representative of semantic meanings of the reference text words. Input text words are converted into numerical vectors using the vector space. Word clusters are formed according to semantic similarity between the input text words, where the semantic similarity between pairs of input text words is represented by metric values determined from pairs of numerical vectors. The word clusters define nodes of the reference data structure. A text label is applied to each node of the reference data structure, where the text label is representative of the semantic meaning shared by elements of the word cluster.

Growing community of inventors

Markham, Canada

Haolin Guo