آمار
| تعداد نشریات | 36 |
| تعداد شماره‌ها | 1,192 |
| تعداد مقالات | 8,579 |
| تعداد مشاهده مقاله | 6,989,621 |
| تعداد دریافت فایل اصل مقاله | 4,033,148 |
نهان کاوی گفتار در بیت های کم ارزش بر مبنای درصد نمونه های مجاور یکسان | ||
| پدافند الکترونیکی و سایبری | ||
| مقاله 6، دوره 9، شماره 1 - شماره پیاپی 33، اردیبهشت 1400، صفحه 75-90 اصل مقاله (1.54 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| نویسندگان | ||
| سعید یزدانپناه1؛ محمد خیراندیش* 2؛ محمد مصلح3 | ||
| 1دانشجوی دکتری گروه مهندسی کامپیوتر، واحد دزفول، دانشگاه آزاد اسلامی، دزفول، ایران | ||
| 2استادیار گروه مهندسی کامپیوتر، واحد دزفول، دانشگاه آزاد اسلامی، دزفول، ایران | ||
| 3دانشیار گروه مهندسی کامپیوتر، واحد دزفول، دانشگاه آزاد اسلامی، دزفول، ایران | ||
| تاریخ دریافت: 18 فروردین 1399، تاریخ بازنگری: 21 خرداد 1399، تاریخ پذیرش: 05 آبان 1399 | ||
| چکیده | ||
| عمومیت فایلهای صوتی، اغلب توجه مهاجمین و عناصر مخرب را برای استفاده از این حامل، جهت پوششدهی ارتباطات محرمانه خود جلب می‌نماید. گستردگی استفاده از این قالبها، به‌همراه رویکردهای متعدد و مدرنی که برای نهاننگاری در فایلهای صوتی طراحی شدهاند، میتوانند فضای سایبری را به محیطی نا امن بدل نمایند. در راستای مقابله با این تهدیدات، امروزه روشهای متعدد نهانکاوی ابداع شدهاند که با دقت بالایی قادر به تحلیل آماری قالبهای مختلف صوتی، مانند MP3 و VoIp هستند. در میان راهحلهای ارائه‌شده، ترکیب روشهای پردازش سیگنال و یادگیری ماشین، امکان ایجاد نهانکاوهایی با دقت بسیار بالا را فراهم نموده است. با این وجود، از آنجا که ویژگیهای آماری فایلهای صوتی گفتاری متفاوت از نمونههای دیگر صوتی است، روشهای جاری نهانکاوی قادر نیستند به شکل مؤثری فایلهای حامل گفتاری را تشخیص دهند. مشکل دیگر، ابعاد بالای تحلیلی است که به شکل چشمگیری هزینه پیادهسازی را افزایش میدهد. در پاسخ به مشکلات ذکرشده، این مقاله ویژگی یکبعدی "درصد نمونههای مجاور یکسان" را به‌عنوان فاکتور جداسازی نمونههای نهاننگاری شده از پاک مطرح میکند. نتایج نشانگر حساسیت 82/99% نهانکاو طراحی‌شده با استفاده از دستهبند تابع عضویت گاوسی، در نرخ نهاننگاری 50% است. علاوه بر این، این نهانکاو قادر است با دقت مطلوبی حجم پیام مخفی‌شده را تخمین بزند. عملکرد الگوریتم طراحی‌شده بر روی یک پایگاه داده متشکل از نمونههای موسیقی کلاسیک نیز ارزیابی شده و نتایج حاکی از کارایی 2/81% آن هستند. | ||
| کلیدواژه‌ها | ||
| نهان کاوی گفتار؛ نهان کاوی صوتی؛ پردازش سیگنال های صوتی؛ LSB؛ نهان نگاری | ||
| عنوان مقاله [English] | ||
| Speech Steganalysis of Least Significant Bits Based on the Percentage of Equal Adjacent Samples | ||
| نویسندگان [English] | ||
| S. Yazdanpanah1؛ M. Kheyrandish2؛ M. Mosleh3 | ||
| 1Faculty of computer science, Islamic Azad University, Khorramabad Branch, Khorramabad, Iran | ||
| 2Department of Computer engineering . Dezful Branch. Islamic Azad University. Dezful. Iran | ||
| 3Department of Computer Engineering, Dezful Branch, Islamic Azad University, Dezful, Iran | ||
| چکیده [English] | ||
| The popularity of audio formats usually attracts the attention of intruders and criminals to use this medium as a cover for establishing their secret communications. The extensive use of this formats, along with various modern techniques, designed for audio steganography, can cause the cyber spaces to be insecure environments. In order to deal with threats, some audio steganalysis techniques have been presented that statistically analyze various audio formats, such as music, MP3, and VoIP, efficiently. Among the presented approaches, combining the techniques of signal processing and machine learning has made possible the creation of steganalyzers that are highly accurate. However, since the statistical properties of audio files differ from purely speech ones, the current steganalysis methods cannot detect speech stego files, accurately. Another issue is the large number of analysis dimensions which increase the implementation cost, significantly. As response to these issues, this paper proposes the percentage of equal adjacent samples (PEAS) feature, as a one-dimensional feature for speech steganalysis. Using a classifier, based on the Gaussian membership function, on stego instances with 50% embedding ratio, the evaluation results for the designed steganalyzer, show a sensitivity of 99.82%. Additionally, it can efficiently estimate the length of a hidden message with the desirable accuracy. Also, the PEAS steganalysis was evaluated on a database, containing classic music instances, and the results show an 81.2% efficient performance. | ||
| کلیدواژه‌ها [English] | ||
| Speech steganalysis, audio steganalysis, digital signal processing, LSB, Steganography | ||
| مراجع | ||
|
[1] H. Ghasemzadeh and M. H. Kayvanrad, “Comprehensive review of audio steganalysis methods,” IET Signal Process, vol. 12, pp. 673-687, 2018.## [2] S. S. Chaeikar, M. Zamani, A. B. A. Manaf, and A. M. Zeki, “PSW statistical LSB image steganalysis,” Multimed. Tools Appl., vol. 77, pp. 805-835, 2018.## [3] S. S. Chaeikar and A. Ahmadi, “Ensemble SW image steganalysis: A low dimension method for LSBR detection,” Signal Process. Image Commun, vol. 70, pp. 233-245, 2019.## [4] Y. Khorasani, J. Mazloum, and M. Shayesteh Far, “Increasing Insertion Capacity and Resistance in Image Steganography Based on Mapping and Bits Reduction,” Journal of electronical and cyber defence, vol. 7, pp. 33-40, 2019. (In Persian)## [5] S. S. Chaeikar, A. A. Manaf, A. Alarood, and M. Zamani, “PFW: Polygonal Fuzzy Weighted—An SVM Kernel for the Classification of Overlapping Data Groups,” Electronics, vol. 9, p. 615, 2020.## [6] M. Zamani, A. A. Manaf, R. Ahmad, F. Jaryani, H. Taherdoost, S. S. Chaeikar, and H. R. Zeidanloo, “A novel approach for genetic audio watermarking,” Journal of Information Assurance and Security, vol. 5, pp. 102-111, 2010.## [7] M. Shahrezaei, and N. Razmjoei, “A New Method for Image Steganography Using Discrete Wavelet Transforms,” Journal of electronical and cyber defence, vol. 7, pp. 83-92, 2019. (In Persian)## [8] W. Bender, D. Gruhl, N. Morimoto, and A Lu, “Techniques for data hiding,” IBM Syst. J., vol. 35, pp. 313-336, 1996.## [9] W. Zeng, H. Ai, and R. Hu, “A novel steganalysis algorithm of phase coding in audio signal,” presented at the Sixth International Conference on Advanced Language Processing and Web Information Technology, 2007.## [10] R. M. Nugraha, “Implementation of direct sequence spread spectrum steganography on audio data,” International Conference on Electrical Engineering and Informatics, 2011.## [11] Y. C. Qi, L. Ye, and C. Liu, “Wavelet domain audio steganalysis for multiplicative embedding model,” International Conference on Wavelet Analysis and Pattern Recognition, 2009.## [12] I. Avcibas, “Audio steganalysis with content-independent distortion measures,” IEEE Signal Process. Lett., vol. 13, pp. 92-95, 2006.## [13] M. K. Johnson, S. Lyu, and H. Farid, “Steganalysis of recorded speech,” Security, Steganography, and Watermarking of Multimedia Contents VII, vol. 5681, pp. 664-672, 2005.## [14] H. Ghasemzadeh and M. K. Arjmandi, “Universal audio steganalysis based on calibration and reversed frequency resolution of human auditory system,” IET Signal Process, vol. 11, pp. 916-922, 2017.## [15] X. M. Ru, H. J. Zhang, and X. Huang, “Steganalysis of audio: Attacking the steghide,” International Conference on Machine Learning and Cybernetics, 2005.## [16] J. W. Fu, Y. C. Qi, and J. S. Yuan, “Wavelet domain audio steganalysis based on statistical moments and PCA,” International Conference on Wavelet Analysis and Pattern Recognition, 2007.## [17] O. H. Kocal, E. Yuruklu, and E. Dilaveroglu, “Speech steganalysis based on the delay vector variance method,” Turk. J. Elec. Eng. & Comp. Sci., vol. 24, pp. 4129-4141, 2016.## [18] Q. Liu, A. H. Sung, and M. Qiao, “Temporal derivative-based spectrum and mel-cepstrum audio steganalysis,” IEEE Trans. Inf. Forensics Secur., vol. 4, pp. 359-368, 2009.## [19] C. Kraetzer and J. Dittmann, “Mel-cepstrum based steganalysis for VoIP steganography,” Security, steganography, and watermarking of multimedia contents IV, vol. 6505, 2007.## [20] H. Ghasemzadeh, M. K. Arjmandi, “Reversed-Mel cepstrum based audio steganalysis”, 4th International Conference on Computer and Knowledge Engineering, 2014.## [21] C. Han, R. Xue, R. Zhang, and X. Wang, “A new audio steganalysis method based on linear prediction,” Multimed. Tools. Appl., vol. 77, pp. 15431-15455, 2018.## [22] F. Djebbar, and B. Ayad, “Audio steganalysis based on lossless data-compression techniques,” International Conference on Information and Communications Security, 2012.## [23] Y. Tint, and K. T. Mya, “Audio steganalysis using features extraction and classification,” International Journal of Research and Reviews in Computer Science, vol. 3, 2012.## [24] H. Ghasemzadeh, M. T. Khass, and M. K. Arjmandi, “Audio steganalysis based on reversed psychoacoustic model of human hearing,” Digit. Signal Process., vol. 51, pp. 133-141, 2016.## [25] U. Yavanoglu, B. Ozcakmak, and O. Milletsever, “A new intelligent steganalysis method for waveform audio files,” 11th International Conference on Machine Learning and Applications, 2012.## [26] X. Yu, R. Wang, D. Yan, and J. Zhu, “MP3 audio steganalysis using calibrated side information feature,” J. Comput. Inf. Syst., vol. 8, pp. 4241-4248, 2012.## [27] D. Yan, R. Wang, X. Yu, and J. Zhu, “Steganalysis for MP3Stego using differential statistics of quantization step,” Digit. Signal Process., vol. 23, pp. 1181-1185, 2013.## [28] Y. Ren, T. Cai, M. Tang, and L. Wang, “AMR steganalysis based on the probability of same pulse position,” IEEE Trans. Inf. Forensics Secur., vol. 10, pp. 1801-1811, 2015.## [29] H. Miao, L. Huang, Z. Chen, W. Yang, and A. Al-Hawbani, “A new scheme for covert communication via 3G encoded speech,” Comput. Electr. Eng., vol. 38, pp. 1490-1501, 2012.## [30] B. Geiser and P. Vary, “High rate data hiding in ACELP speech codecs,” IEEE International Conference on Acoustics, Speech and Signal Processing, 2008.## [31] Y. Ren, Q. Xiong, and L. Wang, “Steganalysis of AAC using calibrated Markov model of adjacent codebook,” IEEE International Conference on Acoustics, Speech and Signal Processing, 2016.## [32] H. Ozer, I. Avcibas, B. Sankur, and N. D. Memon, “Steganalysis of audio based on audio quality metrics,” Security and Watermarking of Multimedia Contents V, vol. 5020, pp. 55-66, 2003.## [33] E. Yuruklu, O. H. Kocal, and E. Dilaveroglu, “A new approach for speech audio steganalysis using delay vector variance method,” Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, vol. 19, pp. 27-36, 2014.## [34] O. H. Koçal, E. Yuruklu, and I. & Avcibas, “Chaotic-type features for speech steganalysis,” IEEE Trans. Inf. Forensics Secur., vol. 3, pp. 651-661, 2008.## [35] H. Miao, L. Huang, Y. Shen, X. Lu, and Z. Chen, “Steganalysis of compressed speech based on Markov and entropy,” International Workshop on Digital Watermarking, 2013.## [36] N. Jayasree and P. P. Amritha, “A Model for the Effective Steganalysis of VoIP,” Artificial Intelligence and Evolutionary Algorithms in Engineering Systems, pp. 379-387, New Delhi, 2015.## [37] H. Tian, Y. Wu, C. C. Chang, Y. Huang, J. Liu, T. Wang, and Y. Cai, “Steganalysis of analysis by synthesis speech exploiting pulse position distribution characteristics,” Security and communication networks, vol. 9, pp. 2934-2944, 2016.## [38] J. Chaharlang, M. Mosleh, and S. Rasouli-Heikalabad, “A novel quantum steganography-Steganalysis system for audio signals,” Multimed. Tools Appl., vol. 79, pp. 17551-17577, Feb. 2020.## | ||
|
آمار تعداد مشاهده مقاله: 567 تعداد دریافت فایل اصل مقاله: 357 |
||