Research Article

AUDIO FORGERY DETECTION FROM HIGH-RESOLUTION SPECTROGRAM WITH AKAZE METHOD

Volume: 26 Number: 4 December 3, 2023
EN TR

AUDIO FORGERY DETECTION FROM HIGH-RESOLUTION SPECTROGRAM WITH AKAZE METHOD

Abstract

Copy-paste forgery, which is widely used in the field of audio forgery, is created by copying an audio part in the audio and pasting it in a different location in the same audio. While this type of forgery is quite easy to implement thanks to advanced audio software, post-processing operations applied to forged audio by attackers to hide traces of forgery make this forgery detection extremely difficult. For this purpose, a new post-processing-robust method for detecting audio copy-paste forgery using a key point-based approach on the high-resolution spectrogram image obtained from the audio is proposed. In the proposed method, firstly, a high-resolution spectrogram image is obtained from the audio file. Then, with the Akaze method, key points, and feature descriptors are extracted from the spectrogram image. Extracted features are matched with the g2NN algorithm. Audio copy-paste forgery is detected by tracing the key points on the spectrogram onto the audio. The results obtained show that the proposed method detects audio copy-paste forgery with very high accuracy when compared to the studies in the literature, even if post-processing operations are applied.

Keywords

Supporting Institution

TÜBİTAK

Project Number

122E013

References

  1. Alcantarilla, P. F., Bartoli, A., & Davison, A. J. (2012). KAZE features. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VI 12 (pp. 214-227). Springer Berlin Heidelberg.
  2. Alcantarilla, P. F., Nuevo, J., & Bartoli, A. (2013). Fast explicit diffusion for accelerated features in nonlinear scale spaces british machine vision conference (BMVC).
  3. Amerini, I., Ballan, L., Caldelli, R., Del Bimbo, A., & Serra, G. (2011). A sift-based forensic method for copy–move attack detection and transformation recovery. IEEE transactions on information forensics and security, 6(3), 1099-1110 DOI:10.1109/TIFS.2011.2129512
  4. BURUCU, E. (2023). Adli Bilimlerde Ses Kayıtları Üzerinde Manipülasyon İncelemesi. Hacettepe Üniversitesi Edebiyat Fakültesi Dergisi, 40(1) DOI:10.32600/huefd.1106795
  5. Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), 381-395 DOI:10.1145/358669.358692
  6. Huang, X., Liu, Z., Lu, W., Liu, H., & Xiang, S. (2020). Fast and effective copy-move detection of digital audio based on auto segment. In Digital forensics and forensic Investigations: Breakthroughs in Research and Practice (pp. 127-142). IGI Global DOI:10.4018/IJDCF.2019040104
  7. Imran, M., Ali, Z., Bakhsh, S. T., & Akram, S. (2017). Blind detection of copy-move forgery in digital audio forensics. IEEE Access, 5, 12843-12855 DOI:10.1109/ACCESS.2017.2717842
  8. Nam, J., Mysore, G. J., Ganseman, J., Lee, K., & Abel, J. S. (2010). A super-resolution spectrogram using coupled PLCA. In Eleventh Annual Conference of the International Speech Communication Association.

Details

Primary Language

Turkish

Subjects

Computer Forensics

Journal Section

Research Article

Publication Date

December 3, 2023

Submission Date

July 23, 2023

Acceptance Date

September 28, 2023

Published in Issue

Year 1970 Volume: 26 Number: 4

APA
Üstübioğlu, B., & Tahaoglu, G. (2023). YÜKSEK ÇÖZÜNÜRLÜKLÜ SPEKTROGRAM GÖRÜNTÜLERİNDEN AKAZE YÖNTEMİ İLE SES SAHTECİLİĞİ TESPİTİ. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(4), 961-972. https://doi.org/10.17780/ksujes.1331543

Cited By