METHODS OF COUNTERING SPEECH SYNTHESIS ATTACKS ON VOICE BIOMETRIC SYSTEMS IN BANKING
Annotation
The paper considers methods of countering speech synthesis attacks on voice biometric systems in banking. Voice biometrics security is a large-scale problem significantly raised over the past few years. Automatic speaker verification systems (ASV) are vulnerable to various types of spoofing attacks: impersonation, replay attacks, voice conversion, and speech synthesis attacks. Speech synthesis attacks are the most dangerous as the technologies of speech synthesis are developing rapidly (GAN, Unit selection, RNN, etc.). Anti-spoofing approaches can be based on searching for phase and tone frequency anomalies appearing during speech synthesis and on a preliminary knowledge of the acoustic differences of specific speech synthesizers. ASV security remains an unsolved problem, because there is no universal solution that does not depend on the speech synthesis methods used by the attacker. In this paper, we provide the analysis of existing speech synthesis technologies and the most promising attacks detection methods for banking and financial organizations. Identification features should include emotional state and cepstral characteristics of voice. It is necessary to adjust the user’s voiceprint regularly. Analyzed signal should not be too smooth and containing unnatural noises or sharp interruptions changes in the signal level. Analysis of speech intelligibility and semantics are also important. Dynamic passwords database should contain words that are difficult to synthesize and pronounce. The proposed approach could be used for design and development of authentication systems for banking and financial organizations resistant to speech synthesis attacks.
Keywords
Постоянный URL
Articles in current issue
- ON SAFETY ISSUE OF INDUSTRIAL CONTROL SYSTEMS
- AN ANALYSIS OF ADDITIONAL ERRORS OF THE OPTICAL-ELECTRONIC SYSTEM FOR MONITORING THE RAILWAY TRACK POSITION
- ON THE CHOICE OF THE APERTURE DIAMETER OF THE PROBE LASER IN GROUND-BASED ADAPTIVE OPTOELECTRONIC SYSTEMS IN THE FORMATION OF A SODIUM REFERENCE STAR
- APPROACH TO GETTING IMAGES OF OBJECTS BASED ON INDIRECT LASER LOCATION DATA
- DESIGN STRATEGY AND MANAGEMENT OF ABERRATION CORRECTION PROCESS FOR LENS WITH HIGH COMPLEXITY INDEX
- FOURIER SPECTROSCOPY IN BLOOD PLASMA STUDY WITH TYPE TWO DIABETES
- DEFOCUS IMPACT ANALYSIS ON TELESCOPE WAVEFRONT RECONSTRUCTION BY SCATTERING SPOT WITH PARAMETRIC OPTIMIZATION TECHNIQUE
- APPLICATION PROSPECTS FOR UNMANNED TRANSPORT SHIPS IN THE SEAS OF THE RUSSIAN ARCTIC BASIN
- HUMAN PSYCHE CREATION BY APPLICATION OF NATURAL LANGUAGE PROCESSING TECHNOLOGIES
- GOODPOINT: UNSUPERVISED LEARNING OF KEY POINT DETECTION AND DESCRIPTION
- A QUANTUM-LIKE SEMANTIC MODEL FOR TEXT RETRIEVAL IN ARABIC
- SIMULATION OF PROPAGATION AND DIFFRACTION OF SHOCK WAVE IN PLANAR CURVILINEAR CHANNEL
- ALGORITHM FOR IDENTIFICATION OF DC MOTOR PARAMETERS BY METHOD OF DYNAMIC EXPANSION OF REGRESSOR AND MIXING
- FORECASTING THE SPRING FLOOD OF RIVERS WITH MACHINE LEARNING METHODS
- FLEXIBILITY INSURANCE OF ROBOTIC TECHNOLOGY SYSTEMS FOR ASSEMBLING OF SMALL-SIZED PRODUCTS