Articles producció científica> Enginyeria Informàtica i Matemàtiques

Utility-Preserving Privacy Protection of Textual Documents via Word Embeddings

  • Identification data

    Identifier: imarina:9242167
    Authors:
    Hassan, FadiSanchez, DavidDomingo-Ferrer, Josep
    Abstract:
    A great variety of mechanisms have been proposed to protect structured databases with numerical and categorical attributes; however, little attention has been devoted to unstructured textual data. Textual data protection requires first detecting sensitive pieces of text and then masking those pieces via suppression or generalization. Current solutions rely on classifiers that can recognize a fixed set of (allegedly sensitive) named entities. Yet, such approaches fall short of providing adequate protection because in reality references to sensitive information are not limited to a predefined set of entity types, and not all the appearances of certain entity type result in disclosure. In this work we propose a more general and flexible based on the notion of word embedding. By means of word embeddings we build vectors that numerically capture the semantic relationships of the textual terms. Then we evaluate the disclosure caused by the terms on the entity to be protected according to the similarity between their vector representations. Our method also preserves the semantics (and, therefore, the utility) of the document by replacing risky terms with privacy-preserving generalizations. Empirical results show that our approach offers much more robust protection and greater utility preservation than methods based on named entity recognition. IEEE
  • Others:

    Author, as appears in the article.: Hassan, Fadi; Sanchez, David; Domingo-Ferrer, Josep
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Domingo Ferrer, Josep / Hassan, Fadi Abdulfattah Mohammed / Sánchez Ruenes, David
    Keywords: Word embeddings Vector representations Training data Textual documents Structured database Sensitive informations Semantics Semantic relationships Redaction Privacy protection Privacy preserving Privacy by design Natural language processing systems Named entity recognition Manuals Hidden markov models Embeddings Databases Data protection Data models Categorical attributes word embeddings textual documents redaction named entity recognition
    Abstract: A great variety of mechanisms have been proposed to protect structured databases with numerical and categorical attributes; however, little attention has been devoted to unstructured textual data. Textual data protection requires first detecting sensitive pieces of text and then masking those pieces via suppression or generalization. Current solutions rely on classifiers that can recognize a fixed set of (allegedly sensitive) named entities. Yet, such approaches fall short of providing adequate protection because in reality references to sensitive information are not limited to a predefined set of entity types, and not all the appearances of certain entity type result in disclosure. In this work we propose a more general and flexible based on the notion of word embedding. By means of word embeddings we build vectors that numerically capture the semantic relationships of the textual terms. Then we evaluate the disclosure caused by the terms on the entity to be protected according to the similarity between their vector representations. Our method also preserves the semantics (and, therefore, the utility) of the document by replacing risky terms with privacy-preserving generalizations. Empirical results show that our approach offers much more robust protection and greater utility preservation than methods based on named entity recognition. IEEE
    Thematic Areas: Interdisciplinar Information systems Engineering, electrical & electronic Computer science, information systems Computer science, artificial intelligence Computer science applications Computational theory and mathematics Ciência da computação
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    Author's mail: david.sanchez@urv.cat josep.domingo@urv.cat
    Author identifier: 0000-0001-7275-7887 0000-0001-7213-4962
    Record's date: 2024-10-12
    Papper version: info:eu-repo/semantics/acceptedVersion
    Link to the original source: https://ieeexplore.ieee.org/document/9419784
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Ieee Transactions On Knowledge And Data Engineering. 35 (1): 1058-1071
    APA: Hassan, Fadi; Sanchez, David; Domingo-Ferrer, Josep (2023). Utility-Preserving Privacy Protection of Textual Documents via Word Embeddings. Ieee Transactions On Knowledge And Data Engineering, 35(1), 1058-1071. DOI: 10.1109/TKDE.2021.3076632
    Article's DOI: 10.1109/TKDE.2021.3076632
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2023
    Publication Type: Journal Publications
  • Keywords:

    Computational Theory and Mathematics,Computer Science Applications,Computer Science, Artificial Intelligence,Computer Science, Information Systems,Engineering, Electrical & Electronic,Information Systems
    Word embeddings
    Vector representations
    Training data
    Textual documents
    Structured database
    Sensitive informations
    Semantics
    Semantic relationships
    Redaction
    Privacy protection
    Privacy preserving
    Privacy by design
    Natural language processing systems
    Named entity recognition
    Manuals
    Hidden markov models
    Embeddings
    Databases
    Data protection
    Data models
    Categorical attributes
    word embeddings
    textual documents
    redaction
    named entity recognition
    Interdisciplinar
    Information systems
    Engineering, electrical & electronic
    Computer science, information systems
    Computer science, artificial intelligence
    Computer science applications
    Computational theory and mathematics
    Ciência da computação
  • Documents:

  • Cerca a google

    Search to google scholar