Bezpieczeństwo systemów biometrii głosowej

• Autorzy: Janicki A.

Identyfikatory

DOI

10.15199/59.2017.8-5.3

Warianty tytułu

EN

Security of voice biometric systems

• Konferencja: XXXIII Krajowe Sympozjum Telekomunikacji i Teleinformatyki (XXXIII ;13-15.09.2017 ; Warszawa, Polska)
• Języki publikacji: PL

Abstrakty

PL

Artykuł dotyczy zagadnienia bezpieczeństwa systemów biometrii głosowej, czyli systemów wykorzystujących automatyczną weryfikację mówcy (Automatic Speaker Verification - ASV). Szczególną uwagę poświęcono zagrożeniom atakami przez osoby podszywające się pod inną tożsamość (spoofing). Na wstępie omówiono używane obecnie algorytmy służące do biometrii głosowej. Następnie omówiono główne rodzaje ataków, takich jak atak z użyciem syntezy mowy, konwersji głosu czy odtworzenia nagrania. Przedstawiono również metody, które mają na celu ochronę przed tymi zagrożeniami, wraz z oceną ich skuteczności.

EN

This article concerns the problem of the security of voice biometric systems, i.e., systems which provide automatic speaker verification (ASV). Special attention is given to vulnerability to spoofing attacks. First, the state-of-the-art voice biometric systems are presented, followed by the most common types of spoofing attacks, such as attacks using speech synthesis, voice conversion or replay. Next, the most common spoofing countermeasures are described, together with the assessment of their efficiency.

Słowa kluczowe

PL

biometria głosowa; spoofing; sygnał mowy; weryfikacja mówcy

EN

speech signal; spoofing; speaker verification; voice biometrics

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne
• Rocznik: 2017
• Tom: nr 8-9
• Strony: 653--658
• Opis fizyczny: Bibliogr. 41 poz., rys., tab.

Twórcy

autor

Janicki A.

• Zakład Cyberbezpieczeństwa, Instytut Telekomunikacji, Wydział Elektroniki i Technik Informacyjnych PW

Bibliografia

• [1] Alegre F., A. Amehrave, and N. Evans, "Spoofing countermeasures to protect automatic speaker verification from voice conversion", w. Proc. IEEE Int. Conf. Acoust., Speech and Signal Process (ICASSP), 2013.
• [2] Alegre R, A. Janicki, and N. Evans, "Re-assessing the threat of replay spoofing attacks against automatic speaker verification", in International Conference of the Biometrics Special Interest Group (BIOSIG), str. 1-6, 2014.
• [3] Alegre F., R. Vipperla, A. Amehrave, and N. Evans, "Anew speaker verification spoofing countermeasure based on local binary patterns", w: Proc. Interspeech 2013, Lyon, France, 2013.
• [4] Australian Government, Australian Taxation Office, https://www.ato.gov. au/media-centre/media-releases/ato-launches-voice-authentication/.
• [5] Bank Smart, http://www.banksmart.pi/.aplikacja/biometria/.
• [6] Campbell W. M., "Weighted Nuisance Attribute Projection", w: Proceedings Odyssey 2010, Brno, Czech Rep., 2010.
• [7] Dehak N., R Kenny, R. Dehak, O. Glembek, R Dumouchel, L. Burget, V. Hubeika and F. Castaldo, "Support vector machines and Joint Factor Analysis for speaker verification", w. Proceedings ICASSP 2009.
• [8] De Leon R L., l. Hernaez, l. Saratxaga, M. Pucher, and J. Yamagishi, "Detection of synthetic speech for the problem of imposture", w: Proc. IEEE Int. Conf. Acoust, Speech and Signal Process (ICASSP), str. 4844-4847, 2011.
• [9] Doddington G., W. Liggett, A. Martin, M. Przybocki & D. Reynolds, "Sheep, goats, lambs and wolves: A statistical analysis of speaker performance in the NIST1998 speaker recognition evaluation", raport techniczny, National Inst of Standards And Technology, Gaithersburg MD, 1998.
• [10] Farrus M., M. Wagner, J. Anguita, and J. Hernando, "How vulnerable are prosodic features to professional imitators?" in Proc. IEEE ODYSSEY - The Speaker and Language Recognition Workshop, 2008.
• [11] Gatka J., M. Grzywacz, and R. Samborski, "Playback attack detection for text-dependent speaker verification over telephone channels", Speech Communication, vol. 67, str. 143-153, 2015.
• [12] Janicki A., „Spoofing Countermeasure Based on Analysis of Linear Prediction Error", w: Proc. Interspeech 2015, Drezno, Niemcy, 2015.
• [13] Janicki A., "Increasing anti-spoofing protection in speaker verification using linear prediction", Multimedia Tools and Applications, 76(6), str. 9017-9032, 2016.
• [14] Janicki A., F. Alegre, N. Evans, "An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks", Security and Communication Networks, 9(15), str. 3030-3044, 2016.
• [15] Janicki A., G. Tyszka, Głosowy PIN - uwierzytelnianie użytkownika z wykorzystaniem algorytmu weryfikacji mówcy - XXIII Krajowe Sympozjum Telekomunikacji i Teleinformatyki, Bydgoszcz 2007.
• [16] Kain A., M. Macon, "Spectral voice conversion for text-to-speech synthesis," w; Proc. Of IEEE International Conference on Acoustics, Speech and Signal Processing, vol.1, str. 285-288,1998.
• [17] Kinnunen T, Md Sahidullah, H. Delgado, M. Todisco, N. Evans, J. Yamagishi, K. Lee, "The ASV spoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection", w: Proc. Interspeech 2017, Sztokholm, Szwecja, 2017.
• [18] Kinnunen T, Md Sahidullah, M. Falcone, L. Costantini, R. Gonzalez Hautamaki, D. Thomsen, A. Sarkar, Z. Tan, H. Delgado, M. Todisco, N. Evans, V. Hautamaki, K. Lee, "RedDots replayed: a new replay spoofing attack corpus for text-dependent speaker verification research", w: Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), Nowy Orlean, USA, 2017.
• [19] Kinnunen T, Z. Wu, K. A. Lee, F Sedlak, E. S. Chng, and H. Li, "Vulnerability of Speaker Verification Systems Against Voice Conversion Spoofing Attacks: the case of Telephone Speech", w: Proc. IEEE Int. Conf. Acoust, Speech and Signal Process. (ICASSP), str. 4401-4404, 2012.
• [20] Lau Y W., M. Wagner, and D. Tran, "Vulnerability of speaker verification to voice mimicking", w: Proceedings of IEEE International Symposium on Intelligent Multimedia, Video and Speech Processing, str. 145-148, 2004.
• [21] Majewski W. and R. Staroniewicz, "Imitation of Target Speakers by Different Types of Impersonators", Lecture Notes in Computer Science vol. 6800, ss. 104-112, Springer Berlin Heidelberg, 2011.
• [22] Marcinkowski Z., Biometria głosowa, http://www.biometriaglosowa.pl/2015/01 /polacy-maja-juz-dosc-hase-dostepu.html.
• [23]Masuko T, T. Hitotsumatsu, K. Tokuda, and T. Kobayashi, "On the security of HMM-based speaker verification systems against imposture using synthetic speech", w Proc. EUROSPEECH, 1999.
• [24] Matrouf D., J.-F. Bonastre, and J.-R Costa, "Effect of impostor speech transformation on automatic speaker recognition". Biometrics on the Internet, str. 37, 2005.
• [25] Nuance Vocal Password, http://www.nuance.com/for-business/cus-tomer-service-solutions/voice-biometrics/vocalpassword/.
• [26] Lindberg J. and M. Blomberg, "Vulnerability in speaker verification -a study of technical impostor techniques", in European Conference on Speech Communication and Technology, str. 1211 -1214,1999.
• [27] Ojala T., M. Pietikainen, and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns", Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, str. 971-987, 2002.
• [28] Patel T. B., H. A. Patii, "Combining evidences from mel cepstral, cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech", Proc. Interspeech 2015, Drezno, Niemcy, 2015.
• [29] Petrovska-Delacretaz D. and J. Hennebert, "Text-prompted speaker verification experiments with phoneme specific MLPS", w: Proc. ICASSP'98,1998.
• [30] Przybocki M., Alvin F. Martin. "NIST speaker recognition evaluation chronicles". ODYSSEY04-The Speaker and Language Recognition Workshop, 2004.
• [31] Reynolds D. A., T. F. Quatieri and R. B. Dunn, "Speaker Verification Using Adapted Gaussian Mixture Models", in Digital Signal Processing, 2000.
• [32] Shang W. and M. Stevenson, "Score normalization in playback attack detection", w: IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), str. 1678-1681, March 2010.
• [33] Tatra Banka, http://www.tatrabanka.sk/tlacova-sprava/5122296/svojich-klientov-uz-spozname-po-hlase.html.
• [34]Todisco M., H. Delgado, N. Evans, "Constant Q Cepstral Coefficients: A Spoofing Countermeasure for Automatic Speaker Verification", Computer Speech & Language, Vol. 45, September 2017, ss. 516-535, 2017.
• [35] Villalba J. and E. Lleida, "Preventing replay attacks on speaker verification systems", in IEEE International Carnahan Conference on Security Technology (ICCST), str. 1-8, Oct 2011.
• [36] Villalba J. and E. Lleida, "Speaker verification performance degradation against spoofing and tampering attacks", w: Proc. FALA workshop, str. 131-134,2010.
• [37] Wang Z.-F, G. Wei, and Q.-H. He, "Channel pattern noise based playback attack detection algorithm for speaker recognition," w: Machine Learning and Cybernetics (ICMLC), 20111nternational Conference on, vol. 4, str. 1708-1713, 2011.
• [38] Wu Z., E. Chng, and H. Li, "Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition", w: Proc. 13th Interspeech, 2012.
• [39] Wu Z., N. Evans, T. Kinnunen, J. Yamagishi, F. Alegre, and H. Li, "Spoofing and countermeasures for speaker verification: a survey", Speech Communications, vol. 66, str. 130-153, 2014.
• [40] Wu Z., T. Kinnunen, N. Evans, J. Yamagishi, C. Hanilci, M. Sahidullah, and A. Sizov, "ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures Challenge", in Proc. Interspeech 2015, Drezno, Niemcy, 2015.
• [41] Zen H., T. Nose, J. Yamagishi, S. Sako, T. Masuko, A. W. Black, K. Tokuda, "The HMM-based speech synthesis system (HTS) version 2.O.", 6th ISCA Workshop on Speech Synthesis, Bonn, Germany, August 22-24, 2007.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017)