The efficiency assessment of using hybrid neural networks for the detection of forged audio data in socially oriented systems
DOI:
https://doi.org/10.30837/2522-9818.2024.2.166Keywords:
signal augmentation; vector autoregression; classification; natural language processing; fake information.Abstract
The subject of the research is the problem of detecting falsified data, in particular in audio format, in socially oriented systems. The goal of the work is to develop an effective model based on recurrent and convolutional neural networks for determining the fact of forgery of sound data, using MapReduce technology for parallelization. The article addresses the following tasks: determining the features of audio in socially-oriented systems, conducting an analysis of algorithms for processing audio information both in the form of text and in the form of a signal, forming a list of target architectures of neural networks and revealing the features of their implementation, conducting an experimental test of effectiveness selected approaches. The following methods used are – analytical and inductive method for determining the target set of neural network architectures; expert assessment for the formation of the most influential efficiency factors; experimental, multi-criteria evaluation and statistical methods of data augmentation to determine the most effective model. The following results were obtained: an audio data reprocessing algorithm was developed for the possibility of using recurrent and convolutional networks. Several approaches to data classification using augmentation based on vector autoregression and MapReduce parallelization technology have been implemented. It was determined that the most effective model for the multi-criteria selection problem is a combination of a bidirectional recurrent neural network with support for short- and long-term memory with several convolutional networks. The advantages of using MapReduce technology to optimize training time and data processing are shown, and a set of open questions for further research and applied implementation is defined. Conclusions: he application of an analytical and inductive approach followed by experimental verification made it possible to develop an effective (with an accuracy of more than 96%) a mechanism for detecting fabricated data both in the form of a signal and in text form. The obtained result makes it possible to assert the feasibility of implementing the proposed approach, and, accordingly, makes it possible to reduce the influence of such information in socially oriented systems, especially during crisis events.
References
Список літератури
Anders M. Fake News Detection. European Data Protection Supervisor. URL: https://edps.europa.eu/press-publications/publications/techsonar/fake-news-detection_en (дата звернення: 27.05.2024).
Real-Time Advanced Computational Intelligence for Deep Fake Video Detection / N. Bansal та ін. Applied Science. 2023. Vol. 13 (5). 3095 р. DOI: 10.3390/app13053095
A Signal Detection Approach to Understanding the Identification of Fake News / C. Batailler та ін. Perspectives on Psychological Science. 2023. Vol. 17 (1). Р. 78–98. DOI: 10.1177/1745691620986135
Reis J. Supervised Learning for Fake News Detection / J. C. S. Reis та ін. IEEE Explore. 2019. Vol. 34 (2). Р. 76–81. DOI: 10.1109/MIS.2019.2899143
Giandomenico D. D. Fake news, social media and marketing: A systematic review / D. D. Giandomenico та ін. Journal of Business Research. 2021. Vol. 124. Р. 329–341. DOI: 10.1016/j.jbusres.2020.11.037
Yuan L. Sustainable Development of Information Dissemination: A Review of Current Fake News Detection Research and Practice / L. Yuan та ін. Systems. 2023. Vol. 11 (9). 458 р. DOI: 10.3390/systems11090458
The impact of fake news on social media and its influence on health during the COVID-19 pandemic / Y. M. Rocha та ін. Journal of Public Health. 2023. Vol. 31. Р. 1007–1016. DOI: 10.1007/s10389-021-01658-z
Alonso M. Dataset for multimodal fake news detection and verification tasks / A. Bondielli та ін. Data in Brief. 2024. Vol. 54. 110440 р. DOI: 10.1016/j.dib.2024.110440.
Tolosana R. Sentiment Analysis for Fake News Detection / Tolosana R. та ін. Electronics. 2021. Vol. 10 (11). 1348 р. DOI: 10.3390/electronics10111348
Afanasieva I. Deepfakes and beyond: A Survey of face manipulation and fake detection / Afanasieva I. та ін. Information Fusion. 2020. Vol. 64. Р. 131–148. DOI: 10.1016/j.inffus.2020.06.014
Afanasieva Nataliia Application of Neural Networks to Identify of Fake News / N. Afanasieva та ін. Computational Linguistics and Intelligent Systems, Kharkiv, 20–21 квітня 2023 р. 2023. 3396 р. URL: https://ceur-ws.org/Vol-3396/paper28.pdf (дата звернення: 27.05.2024)
Bhatia Т. Using transfer learning, spectrogram audio classification, and MIT app inventor to facilitate machine learning understanding. Massachusetts Institute of Technology. URL: https://dspace.mit.edu/handle/1721.1/127379 (дата звернення: 27.05.2024).
Breuer A., Eilat R., Weinsberg U. Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks. Web Conference, Taipei, 20–24 квіт. 2023. Р. 1287–1297. DOI: 10.1145/3366423.3380204
Xia T., Chen X. A. Discrete Hidden Markov Model for SMS Spam Detection. Applied Science. 2020. Vol. 10 (14). 5011 р. DOI: 10.3390/app10145011
Najar F., Zamzami N., Bouguila S. Fake News Detection Using Bayesian Inference. Information Reuse and Integration for Data Science, Los Angeles, 30 черв. – 1 серп. 2019. Р. 389–394. DOI: 10.1109/IRI.2019.00066
Montserrat D. Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection / D. M. Montserrat та ін. Workshop on Information Forensics and Security, New York, 6–11 груд. 2020. Р. 1–6. DOI: 10.1109/WIFS49906.2020.9360909
Ning C., You F. Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming. Computers & Chemical Engineering. 2019. Vol. 125. Р. 434–448. DOI: 10.1016/j.compchemeng.2019.03.034
Sardar T. H., Ansari Z. An Analysis of Distributed Document Clustering Using MapReduce Based K-Means Algorithm. Journal of The Institution of Engineers (India):Series B. 2020. Vol. 101. Р. 641–650. DOI: 10.1007/s40031-020-00485-2
Deng R., Duzhin, F. Topological Data Analysis Helps to Improve Accuracy of Deep Learning Models for Fake News Detection Trained on Very Small Training Sets. Big Data and Cognitive Computing. 2022. Vol. 6 (3). 74 р. DOI: 10.3390/bdcc6030074
Choudhary A., Arora A. Linguistic feature based learning model for fake news detection and classification. Expert Systems with Applications. 2021. Vol. 169. 114171 р. DOI: 10.1016/j.eswa.2020.114171
Khovrat A. Parallelization of the VAR Algorithm Family to Increase the Efficiency of Forecasting Market Indicators During Social Disaster / A. Khovrat та ін. Information Technology and Implementation, м. Kyiv, 30 лист. – 2 груд. 2022. Р. 222–233. URL: https://ceur-ws.org/Vol-3347/Paper_19.pdf (дата звернення: 27.05.2024).
References
Anders M. "Fake News Detection. European Data Protection Supervisor", available at: https://edps.europa.eu/press-publications/publications/techsonar/fake-news-detection_en (last accessed 27.05.2024).
Bansal, N., Aljrees, T., Yadav, D. P., Singh, K. U., Kumar, A., Verma, G. K., Singh, T. (2023), "Real-Time Advanced Computational Intelligence for Deep Fake Video Detection", Applied Science, No. 13(5), 3095 р. DOI: 10.3390/app13053095
Batailler, C., Brannon, S. M., Teas, P. E., Gawronski, B. (2023), "A Signal Detection Approach to Understanding the Identification of Fake News", Perspectives on Psychological Science, No. 17(1), P. 78–98. DOI: 10.1177/1745691620986135
Reis, J. C. S., Correia, A., Murai, F., Veloso, A., Benevenuto, F. (2019), "Supervised Learning for Fake News Detection", IEEE Intelligent Systems, No. 34(2), P. 76–81. DOI: 10.1109/MIS.2019.2899143
Giandomenico, D. D., Sit, J., Ishizaka, A., Nunan, D. (2021), "Fake news, social media and marketing: A systematic review", Journal of Business Research, Vol. 124, P. 329–341. DOI: 10.1016/j.jbusres.2020.11.037
Yuan, L., Jiang, H., Shen, H., Shi, L., Cheng, N. (2023), "Sustainable Development of Information Dissemination: A Review of Current Fake News Detection Research and Practice", Systems, No. 11(9), 458 р. DOI: 10.3390/systems11090458
Rocha, Y. M., de Moura, G. A., Desiderio, G. A., de Oliveira, C. H., Lourenço, F. D., de Figueiredo Nicolete, L. D. (2023), "The impact of fake news on social media and its influence on health during the COVID-19 pandemic: a systematic review", Journal of Public Health, Vol. 31, P. 1007–1016. DOI: 10.1007/s10389-021-01658-z
Alonso, M. A., Vilares, D., Gómez-Rodríguez, C., Vilares, J. (2021), "Sentiment Analysis for Fake News Detection", Electronics, No. 10(11), 1348 р. DOI: 10.3390/electronics10111348
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., Ortega-Garcia, J. (2020), "Deepfakes and beyond: A Survey of face manipulation and fake detection", Information Fusion, Vol. 64, P. 131–148. DOI: 10.1016/j.inffus.2020.06.014
Afanasieva, I., Golian, N., Golian, V., Khovrat, A., Onyshchenko, K. (2023), "Application of Neural Networks to Identify of Fake News". Computational Linguistics and Intelligent Systems (COLINS 2023): 7th International Conference, Kharkiv, 20 April – 21 April 2023: CEUR workshop proceedings, No. 3396, P. 346–358, available at: https://ceur-ws.org/Vol-3396/paper28.pdf (last accessed: 27.05.2023).
Afanasieva Nataliia Application of Neural Networks to Identify of Fake News (2023), / N. Afanasieva et al. Computational Linguistics and Intelligent Systems, Kharkiv, 20–21.04.2023. 3396 р. available at: https://ceur-ws.org/Vol-3396/paper28.pdf (last accessed: 27.05.2024)
Bhatia, N. (2020), "Using transfer learning, spectrogram audio classification, and MIT app inventor to facilitate machine learning understanding", Massachusetts Institute of Technology, available at: https://dspace.mit.edu/handle/1721.1/127379
(last accessed 27.05.2024)
Breuer, A., Eilat, R., Weinsberg, U. (2023), "Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks", Web Conference, 20–24 April 2023, Taipei, P. 1287–1297. DOI: 10.1145/3366423.3380204
Xia, T., Chen, X. A. (2020), "Discrete Hidden Markov Model for SMS Spam Detection", Applied Science, Vol. 10 (14), 5011 р. DOI: 10.3390/app10145011
Najar, F., Zamzami, N., Bouguila, S. (2019), "Fake News Detection Using Bayesian Inference", Information Reuse and Integration for Data Science, 30 July – 1 August 2019, Los Angeles, P. 389–394. DOI: 10.1109/IRI.2019.00066
Montserrat, D. M., Horváth, J., Yarlagadda, S. K., Zhu, F., Delp, E. J. (2020), "Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection". Workshop on Information Forensics and Security (WIFS 2020): 12th IEEE International Workshop, New York, 6 December – 11 December 2020: IEEE, P. 1–6. DOI: 10.1109/WIFS49906.2020.9360909
Ning, C., You, F. (2019), "Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming", Computers & Chemical Engineering, Vol. 125, P. 434–448. DOI: 10.1016/j.compchemeng.2019.03.034
Sardar, T. H., Ansari, Z. (2020), "An Analysis of Distributed Document Clustering Using MapReduce Based K-Means Algorithm", Journal of The Institution of Engineers (India): Series B, Vol. 101, P. 641–650. DOI: 10.1007/s40031-020-00485-2
Deng, R., Duzhin, F. (2022), "Topological Data Analysis Helps to Improve Accuracy of Deep Learning Models for Fake News Detection Trained on Very Small Training Sets", Big Data and Cognitive Computing, Vol. 6 (3), 74 р. DOI: 10.3390/bdcc6030074
Choudhary, A., Arora, A. (2021), "Linguistic feature based learning model for fake news detection and classification", Expert Systems with Applications, Vol. 169, Article 114171. DOI: 10.1016/j.eswa.2020.114171
Khovrat, A., Kobziev, V., Nazarov, A., Yakovlev, S. (2022), "Parallelization of the VAR Algorithm Family to Increase the Efficiency of Forecasting Market Indicators During Social Disaster". Information Technology and Implementation (IT&I 2022): 9th Internaional Conference, Kyiv, 30 November – 2 December 2022: CEUR Workshop Proceedings. No. 3347, P. 222–233, available at: https://ceur-ws.org/Vol-3347/Paper_19.pdf (last accessed: 27.05.2024).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Our journal abides by the Creative Commons copyright rights and permissions for open access journals.
Authors who publish with this journal agree to the following terms:
Authors hold the copyright without restrictions and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-commercial and non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their published work online (e.g., in institutional repositories or on their website) as it can lead to productive exchanges, as well as earlier and greater citation of published work.
