Voice Spoofing Research Articles

Voice spoofing detection based on acoustic and glottal flow features using conventional machine learning techniques

Voice spoofing detection based on acoustic and glottal flow features using conventional machine learning techniques

A robust voice spoofing detection system using novel CLS-LBP features and LSTM

Automatic Speaker Verification (ASV) systems are vulnerable to a variety of voice spoofing attacks, e.g., replays, speech synthesis, etc. The imposters/fraudsters often use different voice spoofing attacks to fool the ASV systems to achieve certain objectives, i.e., bypass the security of someone’s home or stealing money from a bank account, etc. To counter such fraudulent activities on the ASV systems, we propose a robust voice spoofing detection system capable of effectively detecting multiple types of spoofing attacks. For this purpose, we propose a novel feature descriptor Center Lop-Sided Local Binary Patterns (CLS-LBP) for audio representation. CLS-LBP effectively analyzes the audios bidirectionally to better capture the artifacts of synthetic speech, microphone distortions of replay, and dynamic speech attributes of the bonafide signal. The proposed CLS-LBP features are used to train the long short-term memory (LSTM) network for detection of both the physical- (replay) and logical-access attacks (speech synthesis, voice conversion). We employed the LSTM due to its effectiveness to better process and learn the internal representation of sequential data. More specifically, we obtained an equal error rate (EER) value of 0.06% on logical-acess (LA) while 0.58% on physical-access (PA) attacks. Additionally, the proposed system is also capable of detecting the unseen voice spoofing attacks and also robust enough to classify among the cloning algorithms used to synthesize the speech. Performance evaluation on the ASVspoof 2019 corpus signify the effectiveness of the proposed system in terms of detecting the physical- and logical-access attacks over existing state-of-the-art voice spoofing detection systems.

Voice spoofing detector: A unified anti-spoofing framework

Voice controlled systems (VCS) in Internet of Things (IoT), speaker verification systems, voice-based biometrics, and other voice-assistant-enabled systems are vulnerable to different spoofing attacks i.e., replay, cloning, cloned-replay, etc. VCS are not only susceptible to these attacks in a non-network environment, but they are also vulnerable to multi-order spoofing attacks in networked IoT. Additionally, deepfakes with artificially generated audio pose a great threat to the all systems having voice-interfaces. Most of the existing countermeasures against these voice spoofing attacks work for only one specific attack (e.g. voice replay) and fail to generalize this for other classes of spoofing attacks. Additionally, generalization is also crucial for cross-corpora evaluation. Thus, there exists a need to develop a unified voice anti-spoofing framework capable of detecting multiple spoofing attacks. This work presents a unified anti-spoofing framework that uses novel (ATCoP-GTCC) features to combat the variety of voice spoofing attacks. The proposed novel acoustic-ternary co-occurrence patterns (ATCoP) encode the co-occurrence of similar patterns between the center and neighboring samples. Our experiments demonstrate that ATCoP can better capture the microphone induced distortions in replays, unnatural prosody and algorithmic artifacts in cloned samples, and both the distortions and artifacts in cloned-replays including compression on multi-hop attacks in the spoofing samples. The performance of ATCoP could be further enhanced by the Gammatone cepstral coefficients. To evaluate the effectiveness of the proposed anti-spoofing system for multi-order replay and cloned-replay attacks detection, we created a diverse voice spoofing detection corpus (VSDC) containing multi-order replay and cloned-replay audios against the bonafide and cloned audio recordings, respectively. Experimental results obtained on VSDC, ASVspoof 2019, Google’s LJ Speech, and YouTube deepfakes datasets illustrate the effectiveness of the proposed system in terms of accurate detection for a variety of voice spoofing attacks.

A hybrid noise robust model for multireplay attack detection in Automatic speaker verification systems

Biometric Systems are automatic methods of verifying the identity of a person based on some characteristics such as fingerprint, face, speech etc. Speech biometrics involves verifying the identity of a person based on voice. The process is called speaker verification, and such biometric systems are called Automatic Speaker Verification systems. However, these systems are prone to malicious attacks such as replay attacks. Thus, Automatic Speaker Verification systems need to be robust against these attacks. Existing approaches have worked majorly with single-replay attacks. The proposed work in this paper explores three back-end models: Convolutional Neural Network, Long Short-Term Memory and hybrid of these two models, with different input feature formats. It analyses their performance in a diverse multi-replay attack detection scenario, using the Voice Spoofing Detection Corpus. In the frontend of the proposed hybrid system, mel-spectrograms is used as the feature extraction technique for Convolutional Neural Network based model, and Constant-Q Cepstral Coefficient approach is used for extracting features for Long Short-Term Memory based model. A comparison of this hybrid model’s performance is done with past approaches in single-replay attack detection as well. The average Equal Error Rate achieved on the test set was 0.036 for single-replayed attack and 0.0296 for two times replayed. The hybrid model consistently outperforms other models with lower Equal Error Rate values, thus showing promising results, paving the way for future research along this line. Further, an analysis on unseen noisy audio files suggests the proposed model’s utility in noise-robust systems as well.

Voice Spoofing Countermeasure Based on Spectral Features to Detect Synthetic Attacks Through LSTM

With the growing number of voice-controlled devices, it is necessary to address the potential vulnerabilities of Automatic Speaker Verification (ASV) against voice spoofing attacks such as Physical Access (PA) and Logical Access (LA) attacks. To improve the reliability of ASV systems, researchers have developed various voice spoofing countermeasures. However, it is hard for the voice anti-spoofing systems to effectively detect the synthetic speech attacks that are generated through powerful spoofing algorithms and have quite different statistical distributions. More importantly, the speedy improvement of voice spoofing structures is producing the most effective attacks that make ASV structures greater vulnerable to stumble on those voice spoofing assaults. In this paper, we proposed a unique voice spoofing countermeasure which is successful to hit upon the LA attacks (i.e., artificial speech and transformed speech) and classify the spoofing structures by the usage of Long Short-Term Reminiscence (LSTM). The novel set of spectral features i.e., Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Cepstral Coefficients (GTCC), and spectral centroid are capable to seize maximum alterations present in the cloned audio. The proposed system achieved remarkable accuracy of 98.93%, precision of 100%, recall of 92.32%, F1-score of 96.01%, and an Equal Error Rate (EER) of 1.30%. Our method achieved 8.5% and 7.02% smaller EER than the baseline methods such as Constant-Q Cepstral Coefficients (CQCC) using Gaussian Mixture Model (GMM) and Linear Frequency Cepstral Coefficients (LFCC) using GMM, respectively. We evaluated the performance of the proposed system on the standard dataset i.e., ASVspoof2019 LA. Experimental results and comparative analysis with other existing state-of-the-art methods illustrate that our method is reliable and effective to be used for the detection of voice spoofing attacks.

Mining Hidden Partitions of Voice Utterances using Fuzzy Clustering for Generalized Voice Spoofing Countermeasures

Mining Hidden Partitions of Voice Utterances using Fuzzy Clustering for Generalized Voice Spoofing Countermeasures

Towards protecting cyber-physical and IoT systems from single- and multi-order voice spoofing attacks

Voice-controlled systems (VCSs), a new class of cyber-physical systems (CPS), and Internet of Things (IoT) devices are increasingly employing smart speakers such as Google Home and Amazon Alexa, and other voice assistants to enable management of various remote operations at home and offices. However, these smart speakers and hence VCSs are susceptible to various voice spoofing attacks i.e. replay, cloning, etc., in a non-network environment as well as in a multi-hop network setup. These diverse spoofing threats on VCSs require an urgent need to develop a robust spoofing countermeasure for VCSs capable of detecting a variety of voice spoofing attacks. This paper presents a spoofing countermeasure that uses novel acoustic ternary patterns (ATP) with Gammatone cepstral coefficients (GTCC) features to counter the voice spoofing attacks on VCSs in single- and multi-hop network environments. Our experimental analysis demonstrates that the proposed ATP features when combined with GTCC can effectively detect the distortions in replayed samples, unnatural prosody present in the cloned samples, and both distortions and unnatural patterns of stress and intonation in cloned-replay samples. The proposed ATP-GTCC features are used to train the SVM for development of a spoofing countermeasure to cater all possible forgeries. Experimental results based on highly diversified ASVspoof 2019 and VSDC datasets signify the effectiveness of the proposed countermeasure for reliable detection of 1st- and 2nd-order replay, cloning, and cloned-replay attacks.

The practice of technological deception in videoconferencing systems for distance learning and ways to counter it

This article raises the problem of high-tech deception using video conferencing means during distance learning, which is of increased relevance due to the digitalization of the educational process, with the growth of digital literacy of young people. The article presents some methods of fraud, including a relatively new technology that is very popular: Deepfake. The article details two popular tools for replacing faces, each of which provides step-by-step instructions on how to create, configure and apply in life. The organizational methods that are presented will help teachers detect even the most disguised forgery, including future voice spoofing, and stop any attempt at deception. At the end of the article, the system is described with the help of the technologies that used to combat deepfakes, and an assessment of the danger of existing tools is given. The objectives of this article are to raise public interest in the problem of face substitution and high-tech deception in general, to create grounds for discussing the need to switch to a remote format of events, to broaden the horizons of the reader and provide him with an area for further work and research.

One-Class Learning Towards Synthetic Voice Spoofing Detection

Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion. Recently, researchers developed anti-spoofing techniques to improve the reliability of ASV systems against spoofing attacks. However, most methods encounter difficulties in detecting unknown attacks in practical use, which often have different statistical distributions from known attacks. Especially, the fast development of synthetic voice spoofing algorithms is generating increasingly powerful attacks, putting the ASV systems at risk of unseen attacks. In this work, we propose an anti-spoofing system to detect unknown synthetic voice spoofing attacks (i.e., text-to-speech or voice conversion) using one-class learning. The key idea is to compact the bona fide speech representation and inject an angular margin to separate the spoofing attacks in the embedding space. Without resorting to any data augmentation methods, our proposed system achieves an equal error rate (EER) of 2.19% on the evaluation set of ASVspoof 2019 Challenge logical access scenario, outperforming all existing single systems (i.e., those without model ensemble).

Voice Spoofing Countermeasure for Logical Access Attacks Detection

Voice-driven devices (VDDs) like Google Home and Amazon Alexa, which are well-known connected devices in consumer IoT, have applications in various domains i.e., home appliances automation, next-generation vehicles, voice banking, and so on. However, these VDDs that are based on automatic speaker verification systems (ASVs) are vulnerable to voice based logical access (LA) attacks like Text-to-Speech (TTS) synthesis and converted voice signals. Intruders can exploit these attacks to bypass the security of such systems and gain access of victim’s bank account or home control. Thus, there exists a need to develop an effective voice spoofing countermeasure that can reliably be used to protect these VDDs against such malicious attacks. This work presents a novel audio features descriptor named as extended local ternary pattern (ELTP) to capture the vocal tract dynamically induced attributes of bonafide speech and algorithmic artifacts in synthetic and converted speeches. We fused our novel ELTP features with the linear frequency cepstral coefficients (LFCC) to further strengthen the capability of our features for capturing the traits of bonafide and spoofed signals. We employ the proposed ELTP-LFCC features to train the deep bidirectional Long Short-Term Memory (DBiLSTM) network for classification of the bonafide and spoof signal (i.e., TTS synthesis, converted speech). Performance of our spoofing countermeasure is measured on the large-scale and diverse ASVspoof 2019 logical access dataset. Experimental results demonstrate that the proposed audio spoofing countermeasure can reliably be used to detect the LA spoofing attacks.

A Light-Weight Replay Detection Framework For Voice Controlled IoT Devices

The growing number of voice-controlled devices (VCDs), i.e. Google Home, Amazon Alexa, etc., has resulted in automation of home appliances, smart gadgets, and next generation vehicles, etc. However, VCDs and voice-activated services i.e. chatbots are vulnerable to audio replay attacks. Our vulnerability analysis of VCDs shows that these replays could be exploited in multi-hop scenarios to maliciously access the devices/nodes attached to the Internet of Things. To protect these VCDs and voice-activated services, there is an urgent need to develop reliable and computationally efficient solutions to detect the replay attacks. This paper models replay attacks as a nonlinear process that introduces higher-order harmonic distortions. To detect these harmonic distortions, we propose the acoustic ternary patterns-gammatone cepstral coefficient (ATP-GTCC) features that are capable of capturing distortions due to replay attacks. Error correcting output codes model is used to train a multi-class SVM classifier using the proposed ATP-GTCC feature space and tested for voice replay attack detection. Performance of the proposed framework is evaluated on ASVspoof 2019 dataset, and our own created voice spoofing detection corpus (VSDC) consisting of bona-fide, first-order replay (replayed once), and second-order replay (replayed twice) audio recordings. Experimental results signify that the proposed audio replay detection framework reliably detects both first and second-order replay attacks and can be used in resource constrained devices.

Voice spoofing detection corpus for single and multi-order audio replays

The evolution of modern voice-controlled devices (VCDs) has revolutionized the Internet of Things (IoT) and resulted in the increased realization of smart homes, personalization, and home automation through voice commands. These VCDs can be exploited in IoT driven environments to generate various spoofing attacks, including the chaining of replay attacks (i.e. multi-order replay attacks). Existing datasets like ASVspoof 2017, ASVspoof 2019, and ReMASC contain only first-order replay recordings (i.e. replayed once); therefore, they cannot offer evaluation of anti-spoofing algorithms capable of detecting multi-order replay attacks. Additionally, large-scale datasets like ASVspoof 2017 and ASVspoof 2019 do not capture the characteristics of microphone arrays, which are an essential characteristic of modern VCDs. Therefore, there exists a need for a diverse replay spoofing detection corpus that consists of multi-order replay recordings against bona fide voice samples. This paper presents a novel voice spoofing detection corpus (VSDC) to evaluate the performance of multi-order replay anti-spoofing methods. The proposed VSDC consists of first-order (i.e. replayed once) and second-order replay (i.e. replayed twice) samples against the bona fide audio recordings. We ensured to create a diverse replay spoofing detection corpus in terms of environments, recording and playback devices, speakers, configurations, replay scenarios, etc. More specifically, we used 35 microphones, 25 different recording configurations, and 60 different playback configurations for first- and second-order replays to generate a total of 14,050 samples belonging to 19 speakers. Additionally, the proposed VSDC can also be used to evaluate the performance of speaker verification systems in terms of independent speaker verification. To the best of our knowledge, this is the first publicly available replay spoofing detection corpus comprised of first and second-order replay samples. Experimental results signify the effectiveness of the proposed VSDC in terms of evaluating the performance of anti-spoofing methods under multi-order replay attacks and diverse conditions.

Generalized end-to-end detection of spoofing attacks to automatic speaker recognizers

As automatic speaker recognizer systems become mainstream, voice spoofing attacks are on the rise. Common attack strategies include replay, the use of text-to-speech synthesis, and voice conversion systems. While previously-proposed end-to-end detection frameworks have shown to be effective in spotting attacks for one particular spoofing strategy, they have relied on different models, architectures, and speech representations, depending on the spoofing strategy. In practice, however, one does not have a priori information regarding the strategy an attacker might employ to fool a speaker recognizer, thus it is necessary to devise approaches which are able to detect attacks regardless of the strategy employed to generate them. In this work, we introduce an end-to-end ensemble based approach such that two models – previously shown to perform well on each considered attack strategy – are trained jointly, while a third model learns how to mix their outputs yielding a single score. Experimental results with replay and text-to-speech/voice conversion attacks show the proposed ensemble method achieving similar or superior performance when compared to systems specialized on each spoofing strategy separately.

Acoustic features exploration and examination for voice spoofing counter measures with boosting machine learning techniques

Abstract Automatic Speaker verification systems are vulnerable to spoofing attacks. We propose our anti-spoofing system. It uses some acoustic features. The set of binary classifiers includes XGBoost tree boosting algorithm. ASV Spoof 2015 corpus is utilized in the experiments as the main database for anti-spoofing systems training. The pretreatment of acoustic features is essential for better performance of the system. Obtained results demonstrate that the proposed system can provide a good accuracy. High evaluation performance can be obtained using the combination between MFCC, LogFBE and SSC features. The attained metrics values such 97.80% for the accuracy, 97.12% for the precision, 98.50% for the Recall and 97.81% for the F1-mesure validate the performance of the proposed technique.

Sound Scene and Events Detection using Deep Learning in the Scope of Cyber Security for Multimedia Systems

In addition to many natural sound sources in nature, synthetic sounds are also used in the multimedia systems of our modern world. Environments (i.e., sound scenes) with these sounds are important for biometric authorization, security requirements and robust/safer voice/video communication. Apart from audio formats that have special constraints such as speech/speaker recognition and verification, the separation of polyphonic sounds, noise reduction, detection of sound scenes/events and voice tagging processes are gaining importance in order to create safer information systems in terms of cyber security. In recent years deep learning has been preferred in the field of cyber security due to its layered infrastructure, which enables the easy extraction of attributes and semantic relationships in the raw data. In this study, the use of deep learning architecture models for voice (or speech) analysis and classification/prediction and detection as multimedia data in cyber security coverage is examined. In our study, deep neural networks, convolutional neural networks, recurrent neural networks, restricted Boltzmann machine and deep belief networks are systematically reviewed as prominent models in the publications between 2015 and 2019. Therefore, the orientation in the literature on voice/speech processing in cyber security, prevention of voice spoofing, and achieving consistent and high performance results is clearly demonstrated through discussions and comments based on scientific findings over fourty studies.