Abstract
Steganography is the art of concealing a message within a cover media with the least understandable changes. On the other hand, steganalysis algorithms try to distinguish information-carrying signals from clean signals. This paper proposes a new approach to audio steganalysis that uses fractal dimensions as features and convolutional neural network (CNN) as a classifier. Fractal dimensions are extracted using Higuchi’s, Katz’s, and Petrosian’s algorithms. Hide4PGP and StegHide are the two steganography tools employed at different embedding rates. In order to evaluate the proposed audio steganalysis system, we use 10 audio samples, consisting of 4000 clean and steganographic frames. The proposed system has been compared with several audio steganalysis systems based on MFCC, Wavelet, 2D-MFCC, R-MFCC and LPC as well as classifiers LDA, SVM and KNN. According to the experiment results, the proposed audio steganalysis system shows a so better performance than other systems and brings above 99.5%.
Similar content being viewed by others
References
A Al-Juaid N, Gutub AA, Khan EA (2018) Enhancing PC data security via combining RSA cryptography and video based steganography. J Inform Sec Cyber Res (JISCR) 1(1):8–18
Abu-Marie W, Gutub A, Abu-Mansour H (2010) Image based steganography using truth table based and determinate Array on RGB Indicator. Int J Signal Image Process 1(3):196–204
Al-Otaibi NA, Gutub AA (2014) Flexible stego-system for hiding text in images of personal computers based on user security priority. Int Conf Adv Eng Technol : Dubai UAE: 250–256
Burrough P (1981) Fractal dimensions of landscapes and other environmental data. Nature 294(5838):240
Esteller R et al (2001) A comparison of waveform fractal dimension algorithms. IEEE Trans Circ Syst I: Funda Theory Appl 48(2):177–183
Geetha S, Ishwarya N, Kamaraj N (2010) Audio steganalysis with Hausdorff distance higher order statistics using a rule based decision tree paradigm. Expert Syst Appl 37(12):7469–7482
Ghasemzadeh H, Khass MT, Arjmandi MK (2016) Audio steganalysis based on reversed psychoacoustic model of human hearing. Digit Signal Process 51:133–141
Goh C et al. (2005) Comparison of fractal dimension algorithms for the computation of EEG biomarkers for dementia. 2nd Int Conf Comput Intell Med Healthcare (CIMED 2005) IEEE: 464–471
Gutub A (2010) Pixel Indicator technique for RGB image steganography. J Emerg Technol Web Intell (JETWI) 2(1):56–64
Gutub AA-A, Al-Juaid N (2018) Multi-bits stego-system for hiding text in multimedia images based on user security priority. J Comput Hardware Eng 1(2)
Gutub A et al. (2008) Pixel indicator high capacity technique for RGB image based Steganography. 5th IEEE Int Workshop Signal Process Appl : University of Sharjah U.A.E: 18–20
Gutub A, Al-Qahtani A, Tabakh A (2009) Triple-A: Secure RGB image steganography based on randomization. IEEE/ACS Int Conf Comput Syst Appl : Rabat, Morocco: 400–403
Han C et al (2018) A new audio steganalysis method based on linear prediction. Multimed Tools Appl 77(12):15431–15455
Hetzl S (2003) StegHide steganography. Available from: http://www.steghide.sourceforge.net/
Johnson MK, Lyu S, Farid H (2005) Steganalysis of recorded speech. Sec Steganog Watermark Multimed Contents VII. Int Soc Optics Photonics: 664–673
Khan F, Gutub A (2007) Message concealment techniques using image based steganography. 4th IEEE GCC Conf Exhib Gulf Int Conven Centre: Manamah, Bahrain: 11–14
Kocal OH, Yuruklu E, Avcibas I (2008) Chaotic-type features for speech steganalysis. IEEE Trans Inform Forensics Sec 3(4):651–661
Kraetzer, C. and J. Dittmann (2007) Mel-cepstrum-based steganalysis for VoIP steganography. Sec Steganog Watermark Multimed Contents IX. Int Soc Optics Photonics: 650505
Latifpour H, Mosleh M, Kheyrandish M (2016) An intelligent audio watermarking based on KNN learning algorithm. Int J Speech Technol 18(4):697–706
Li C et al. (2009) Steganalysis of spread spectrum hiding based on DWT and GMM. Int Conf Netw Sec Wireless Commun Trusted Comput IEEE: 240–243
Liu Q, Sung AH, Qiao M (2009) Temporal derivative-based spectrum and mel-cepstrum audio steganalysis. IEEE Trans Inform Forensics Sec 4(3):359–368
Mohsenfar SM, Mosleh M, Barati A (2015) Audio watermarking method using QR decomposition and genetic algorithm. Multimed Tools Appl 74(3):759–779
Mosleh M et al (2016) A robust intelligent audio watermarking scheme using support vector machine. Front Inform Technol Electron Eng 17(12):1320–1330
Ozer H et al. (2003) Steganalysis of audio based on audio quality metrics, in Security and Watermarking of Multimedia Contents V. 2003. Int Soc Opt Photo: 55–67
Paulin C, Selouani S-A, Hervet E (2016) Audio steganalysis using deep belief networks. Int J Speech Technol 19(3):585–591
Paulin C, Selouani S-A, Hervet E (2016) Speech steganalysis using evolutionary restricted Boltzmann machines. IEEE Congress Evol Comput (CEC) IEEE
Petry A, Barone DAC (2002) Speaker identification using nonlinear dynamical features. Chaos, Solitons Fractals 13(2):221–231
Repp H (1996) Hide4PGP steganography. Available from: http://www.heinz-repp.onlinehome.de/Hide4PGP.htm
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Mohtasham-zadeh, V., Mosleh, M. Audio Steganalysis based on collaboration of fractal dimensions and convolutional neural networks. Multimed Tools Appl 78, 11369–11386 (2019). https://doi.org/10.1007/s11042-018-6702-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6702-1