Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks
This paper addresses the detection of hidden information leakage through the use of text steganography. In this paper, we present research results on the study possibility to detect hidden leakages by detecting changes in users writing styles using neural networks and various types of text features....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
FRUCT
2021-05-01
|
| Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| Subjects: | |
| Online Access: | https://www.fruct.org/publications/fruct29/files/Kha.pdf |
| _version_ | 1818864030332223488 |
|---|---|
| author | Alisa Vorobeva Alexander Khazagarov Viktoriia Korzhuk |
| author_facet | Alisa Vorobeva Alexander Khazagarov Viktoriia Korzhuk |
| author_sort | Alisa Vorobeva |
| collection | DOAJ |
| description | This paper addresses the detection of hidden information leakage through the use of text steganography. In this paper, we present research results on the study possibility to detect hidden leakages by detecting changes in users writing styles using neural networks and various types of text features. The framework for hidden leakages detection based on discovering changes in the author's writing style with deep neural networks (RNN, LSTM, GRU) was proposed. To evaluate the hidden leakages detection accuracy were carried out series of experiments on text corpus, contains Russian online texts. The experiments showed that the LSTM and character 4-grams allow achieving the accuracy of 87%. Text preprocessing significantly decreases accuracy. |
| first_indexed | 2024-12-19T10:25:10Z |
| format | Article |
| id | doaj.art-d079ef5a874d434eb18e8246605905be |
| institution | Directory Open Access Journal |
| issn | 2305-7254 2343-0737 |
| language | English |
| last_indexed | 2024-12-19T10:25:10Z |
| publishDate | 2021-05-01 |
| publisher | FRUCT |
| record_format | Article |
| series | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| spelling | doaj.art-d079ef5a874d434eb18e8246605905be2022-12-21T20:25:56ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372021-05-0129117718410.23919/FRUCT52173.2021.9435540Preventing Hidden Information Leaks Using Author Attribution Methods and Neural NetworksAlisa Vorobeva0Alexander Khazagarov1Viktoriia Korzhuk2ITMO University, RussiaITMO University, RussiaITMO University, RussiaThis paper addresses the detection of hidden information leakage through the use of text steganography. In this paper, we present research results on the study possibility to detect hidden leakages by detecting changes in users writing styles using neural networks and various types of text features. The framework for hidden leakages detection based on discovering changes in the author's writing style with deep neural networks (RNN, LSTM, GRU) was proposed. To evaluate the hidden leakages detection accuracy were carried out series of experiments on text corpus, contains Russian online texts. The experiments showed that the LSTM and character 4-grams allow achieving the accuracy of 87%. Text preprocessing significantly decreases accuracy.https://www.fruct.org/publications/fruct29/files/Kha.pdfhidden leakagestext steganographyinformation security |
| spellingShingle | Alisa Vorobeva Alexander Khazagarov Viktoriia Korzhuk Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks Proceedings of the XXth Conference of Open Innovations Association FRUCT hidden leakages text steganography information security |
| title | Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks |
| title_full | Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks |
| title_fullStr | Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks |
| title_full_unstemmed | Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks |
| title_short | Preventing Hidden Information Leaks Using Author Attribution Methods and Neural Networks |
| title_sort | preventing hidden information leaks using author attribution methods and neural networks |
| topic | hidden leakages text steganography information security |
| url | https://www.fruct.org/publications/fruct29/files/Kha.pdf |
| work_keys_str_mv | AT alisavorobeva preventinghiddeninformationleaksusingauthorattributionmethodsandneuralnetworks AT alexanderkhazagarov preventinghiddeninformationleaksusingauthorattributionmethodsandneuralnetworks AT viktoriiakorzhuk preventinghiddeninformationleaksusingauthorattributionmethodsandneuralnetworks |