AUDIO COPY-MOVE FORGERY DETECTION WITH MACHINE LEARNING METHODS

Year 2025, Volume: 26 Issue: 2, 132 - 149, 25.06.2025

Merve Arslan , Şerif Ali Sadık

https://doi.org/10.18038/estubtda.1624909

Abstract

Converting original sounds into fake sounds using various methods and using these sounds for fraud or misinformation purposes poses serious risks and threats. In this study, a classification system using machine learning methods is created and performance analysis is performed in order to detect sounds created with copy-move forgery, which is one of the types of sound forgery. Sound files are treated as raw data. Then, Mel-spectrograms are obtained to visually represent the spectral features of the sound over time. Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN) and XGBoost algorithms are used in the classification phase. As a result of the performance analysis of the created models, the highest success is achieved with the XGBoost algorithm. The performance of the XGBoost algorithm is further improved by performing hyperparameter optimization with the Random Search method. The results of the models are analyzed using various metrics. According to the study results, it is seen that it gives competitive results with the XGBoost algorithm.

Keywords

Audio , Copy-Move Forgery , Machine Learning , XGBoost

References

• [1] Imbwaga JL, Chittaragi NB, Koolagudi SG. Automatic hate speech detection in audio using machine learning algorithms. Int J Speech Technol 2024; 27(2): 447-469.
• [2] Salamon J, Jacoby C, Bello JP. A dataset and taxonomy for urban sound research. In: 22nd ACM International Conference on Multimedia; Nov 2014; pp. 1041-1044. Retrieved 14 December 2020 from https://urbansounddataset.weebly.com/urbansound8k.html.
• [3] Chathuranga S. Sound Event Dataset. [Online]. Retrieved 14 December 2020 from https://github.com/chathuranga95/SoundEventClassification.
• [4] Gourisaria MK, Agrawal R, Sahni M, Singh PK. Comparative analysis of audio classification with MFCC and STFT features using machine learning techniques. Discov Internet Things 2024; 4(1): 1.
• [5] Reimao R, Tzerpos V. For: a dataset for synthetic speech detection. In: 2019 International Conference on Speech Technology and Human–Computer Dialogue (SpeD); 2019. IEEE; pp. 1-10.
• [6] Evgeniou T, Pontil M. Support vector machines: theory and applications. In: Advanced Course on Artificial Intelligence. Berlin: Springer; 1999. pp. 249-257.
• [7] Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T-Y. Lightgbm: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst 2017; 30: 3146-3154.
• [8] Chen T, Guestrin C. Xgboost: a scalable tree boosting system. In: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016. pp. 785-794.
• [9] Guo G, Wang H, Bell D, Bi Y, Greer K. KNN model-based approach in classification. In: OTM Confederated International Conferences on the Move to Meaningful Internet Systems. Berlin: Springer; 2003. pp. 986-996.
• [10] Breiman L. Random forests. Mach Learn 2001; 45(1): 5-32.
• [11] Khochare J, Joshi C, Yenarkar B, Suratkar S, Kazi F. A deep learning framework for audio deepfake detection. Arab J Sci Eng 2021; 1-12.
• [12] Gupta S, Cho S, Kuo CCJ. Current developments and future trends in audio authentication. IEEE Multimedia 2011; 19(1): 50-59.
• [13] Ustubioglu B, Tahaoglu G, Ulutas G. Detection of audio copy-move-forgery with novel feature matching on Mel spectrogram. Expert Syst Appl 2023; 213: 118963.
• [14] Klapuri A, Davy M. Signal processing methods for music transcription. Springer; 2006. ISBN 978-0-387-30667-4.
• [15] Yan Q, Yang R, Huang J. Copy-move detection of audio recording with pitch similarity. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); Apr 2015. IEEE; pp. 1782-1786.
• [16] Wang F, Li C, Tian L. An algorithm of detecting audio copy-move forgery based on DCT and SVD. In: 2017 IEEE 17th International Conference on Communication Technology (ICCT); Oct 2017. IEEE; pp. 1652-1657. [17] Garofolo JS, Lamel LF, Fisher WM, Fiscus JG, Pallett DS. DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST Speech Disc 1-1.1. NASA STI/Recon Tech Rep N 1993; 93: 27403.
• [18] Akdeniz F, Becerikli Y. Detection of copy-move forgery in audio signal with mel frequency and delta-mel frequency kepstrum coefficients. In: 2021 Innovations in Intelligent Systems and Applications Conference (ASYU); 2021. IEEE; pp. 1-6.
• [19] Akdeniz F, Becerikli Y. Detecting audio copy-move forgery with an artificial neural network. Signal Image Video Process 2024; 18(3): 2117-2133.
• [20] Yan Q, Yang R, Huang J. Robust copy-move detection of speech recording using similarities of pitch and formant. IEEE Trans Inf Forensics Secur 2019; 14(9): 2331-2341.
• [21] Shah K, Patel H, Sanghvi D, Shah M. A comparative analysis of logistic regression, random forest and KNN models for the text classification. Augment Hum Res 2020; 5(1): 12.
• [22] Yang Z, Li D. Application of logistic regression with filter in data classification. In: 2019 Chinese Control Conference (CCC); Jul 2019. IEEE; pp. 3755-3759.
• [23] Mondal PK, Foysal KH, Norman BA, Gittner LS. Predicting childhood obesity based on single and multiple well-child visit data using machine learning classifiers. Sensors 2023; 23(2): 759.
• [24] Vapnik VN. The Nature of Statistical Learning Theory. 2nd ed. Springer Verlag; 1995. pp. 1-20.
• [25] Kotsiantis SB. Supervised machine learning: a review of classification techniques. Informatica 2007; 31: 249-268.
• [26] Schnyer DM, Clasen PC, Gonzalez C, Beevers CG. Evaluating the diagnostic utility of applying a machine learning algorithm to diffusion tensor MRI measures in individuals with major depressive disorder. Psychiatry Res Neuroimaging 2017; 264: 1-9.
• [27] Biau G, Scornet E. A random forest guided tour. Test 2016; 25: 197-227.
• [28] Rigatti SJ. Random forest. J Insur Med 2017; 47(1): 31-39.
• [29] Sahour H, Gholami V, Torkaman J, Vazifedan M, Saeedi S. Random forest and extreme gradient boosting algorithms for streamflow modeling using vessel features and tree-rings. Environ Earth Sci 2021; 80: 1-14.
• [30] Kiranmai SA, Laxmi AJ. Data mining for classification of power quality problems using WEKA and the effect of attributes on classification accuracy. Prot Control Mod Power Syst 2018; 3(3): 1-12.
• [31] Bramer M. Principles of data mining. Springer; 2007.
• [32] Ogunleye A, Wang QG. XGBoost model for chronic kidney disease diagnosis. IEEE/ACM Trans Comput Biol Bioinform 2019; 17(6): 2131-2140.
• [33] Wang CC, Kuo PH, Chen GY. Machine learning prediction of turning precision using optimized XGBoost model. Appl Sci 2022; 12(15): 7739.
• [34] Ustubioglu B, Tahaoglu G, Ayaz GO, Ustubioglu A, Ulutas G, Cosar M, Kılıc M. KTUCengAudioForgerySet: a new audio copy-move forgery dataset. In: 2024 47th International Conference on Telecommunications and Signal Processing (TSP); Jul 2024. IEEE; pp. 123-129.
• [35] Su Z, Li M, Zhang G, Wu Q, Wang Y. Robust audio copymove forgery detection on short forged slices using sliding window. Journal of Information Security and Applications, 2023; 75, 103507.
• [36] Yan Q, Yang R, Huang J. Robust copy-move detection of speech recording using similarities of pitch and formant. IEEE Trans. Inform. Forensics Secur., 2019;4(9), 2331–2341.
• [37] Imran M, Al Z, Bakhsh ST, Akram S. Blind detection of copy-move forgery in digital audio forensics. IEEE Access, 2017; 5, 12843–12855.