Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks

Jan Neerbek, Ira Assent, Peter Dolog

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

1 Citation (Scopus)

Abstract

State-of-the-art sensitive information detection in unstructured data relies on the frequency of co-occurrence of keywords with sensitive seed words. In practice, however, this may fail to detect more complex patterns of sensitive information. In this work, we propose learning phrase structures that separate sensitive from non-sensitive documents in recursive neural networks. Our evaluation on real data with human labeled sensitive content shows that our new approach outperforms existing keyword based strategies.
Original languageEnglish
Title of host publicationPAKDD 2018 : Advances in Knowledge Discovery and Data Mining
Number of pages13
Volume10939
PublisherSpringer
Publication date2018
Pages373-385
ISBN (Print)978-3-319-93039-8
ISBN (Electronic)978-3-319-93040-4
DOIs
Publication statusPublished - 2018
Event22nd Pacific-Asia Conference - Melbourne, Australia
Duration: 3 Jun 20186 Jun 2018

Conference

Conference22nd Pacific-Asia Conference
CountryAustralia
CityMelbourne
Period03/06/201806/06/2018
SeriesLecture Notes in Computer Science
ISSN0302-9743

Cite this

Neerbek, J., Assent, I., & Dolog, P. (2018). Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks. In PAKDD 2018: Advances in Knowledge Discovery and Data Mining (Vol. 10939, pp. 373-385). Springer. Lecture Notes in Computer Science https://doi.org/10.1007/978-3-319-93040-4_30
Neerbek, Jan ; Assent, Ira ; Dolog, Peter. / Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks. PAKDD 2018: Advances in Knowledge Discovery and Data Mining. Vol. 10939 Springer, 2018. pp. 373-385 (Lecture Notes in Computer Science).
@inproceedings{71865ad34a944e89a3ddf6a0bc159c0f,
title = "Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks",
abstract = "State-of-the-art sensitive information detection in unstructured data relies on the frequency of co-occurrence of keywords with sensitive seed words. In practice, however, this may fail to detect more complex patterns of sensitive information. In this work, we propose learning phrase structures that separate sensitive from non-sensitive documents in recursive neural networks. Our evaluation on real data with human labeled sensitive content shows that our new approach outperforms existing keyword based strategies.",
author = "Jan Neerbek and Ira Assent and Peter Dolog",
year = "2018",
doi = "10.1007/978-3-319-93040-4_30",
language = "English",
isbn = "978-3-319-93039-8",
volume = "10939",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "373--385",
booktitle = "PAKDD 2018",
address = "Germany",

}

Neerbek, J, Assent, I & Dolog, P 2018, Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks. in PAKDD 2018: Advances in Knowledge Discovery and Data Mining. vol. 10939, Springer, Lecture Notes in Computer Science, pp. 373-385, 22nd Pacific-Asia Conference, Melbourne, Australia, 03/06/2018. https://doi.org/10.1007/978-3-319-93040-4_30

Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks. / Neerbek, Jan; Assent, Ira; Dolog, Peter.

PAKDD 2018: Advances in Knowledge Discovery and Data Mining. Vol. 10939 Springer, 2018. p. 373-385 (Lecture Notes in Computer Science).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks

AU - Neerbek, Jan

AU - Assent, Ira

AU - Dolog, Peter

PY - 2018

Y1 - 2018

N2 - State-of-the-art sensitive information detection in unstructured data relies on the frequency of co-occurrence of keywords with sensitive seed words. In practice, however, this may fail to detect more complex patterns of sensitive information. In this work, we propose learning phrase structures that separate sensitive from non-sensitive documents in recursive neural networks. Our evaluation on real data with human labeled sensitive content shows that our new approach outperforms existing keyword based strategies.

AB - State-of-the-art sensitive information detection in unstructured data relies on the frequency of co-occurrence of keywords with sensitive seed words. In practice, however, this may fail to detect more complex patterns of sensitive information. In this work, we propose learning phrase structures that separate sensitive from non-sensitive documents in recursive neural networks. Our evaluation on real data with human labeled sensitive content shows that our new approach outperforms existing keyword based strategies.

U2 - 10.1007/978-3-319-93040-4_30

DO - 10.1007/978-3-319-93040-4_30

M3 - Article in proceeding

SN - 978-3-319-93039-8

VL - 10939

T3 - Lecture Notes in Computer Science

SP - 373

EP - 385

BT - PAKDD 2018

PB - Springer

ER -

Neerbek J, Assent I, Dolog P. Detecting Complex Sensitive Information via Phrase Structure in Recursive Neural Networks. In PAKDD 2018: Advances in Knowledge Discovery and Data Mining. Vol. 10939. Springer. 2018. p. 373-385. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-93040-4_30