Spoofing Speaker Verification With Voice Style Transfer And Reconstruction Loss (9:20 AM – 9:40 AM)
Thomas Thebaud (Orange), Gaël Le Lan (Orange Labs) and Anthony Larcher (Universite du Mans – LIUM) – On-site presentation
In this paper we investigate a template reconstruction attack against a speaker verification system. A stolen speaker embedding is processed with a zero-shot voice-style transfer system to reconstruct a Mel-spectrogram containing as much speaker information as possible. We assume the attacker has a black box access to a state-of-the-art automatic speaker verification system. We modify the AutoVC voice-style transfer system to spoof the automatic speaker verification system. We find that integrating a new loss targeting embedding reconstruction and optimizing training hyper-parameters significantly improves spoofing. Results obtained for speaker verification are similar to other biometrics, such as handwritten digits or face verification. We show on standard corpora (VoxCeleb and VCTK) that the reconstructed Mel-spectrograms contain enough speaker characteristics to spoof the original authentication system.
Impact of Super-Resolution and Human Identification in Drone Surveillance (9:40 AM – 10:00 AM)
Akshay Agarwal (University at Buffalo), Nalini Ratha (University at Buffalo, SUNY), Mayank Vatsa (IIT Jodhpur) and Richa Singh (IIT Jodhpur) – Virtual presentation
In the scene of large crowd gatherings and challenging visiting places such as rough hills and high glass buildings, acquisition of the images through normal cameras is difficult and next to impossible. In all such scenarios, the drone becomes a useful acquisition sensor to capture the detailed information of the scene and the objects present there. With the rapid development of consumer unmanned aerial vehicles (UAV) or drones, the utilization of these devices became extremely easy. The popular use-case of the drones can be seen for the surveillance to identify any possible threats in the large crowd gathering and recognize the different individuals present in the crowd. However, the images captured using the drones are generally taken from a significant distance to avoid any collision; hence these images generally suffer in quality such as low resolution, motion blur, and other environmental factors. The impact of these artifacts has been seen in the face recognition performance using several machine learning algorithms on large-scale drone databases namely Drone SURF. In this research, we intend to tackle the above artifacts by looking at the problem from the perspective of super-resolution of low-quality images. We have studied state-of-the-art (SOTA) super-resolution algorithms and see whether current methods are capable of handling the challenges of drone images. Apart from that, we have also evaluated another SOTA deep network developed for object detection for human segmentation in drone images. The proposed research provides interesting findings highlighting the limitations of existing works from the perspective of handling drone images. We would like the readers to go through the paper to find out the current limitations and possible future directions in drone image surveillance.
Multi Loss Fusion For Matching Smartphone Captured Contactless Finger Images (10:00 AM – 10:20 AM)
Bhavin Jawade (University at Buffalo), Akshay Agarwal (University at Buffalo), Nalini Ratha (SUNY Buffalo) and Srirangaraj Setlur (University at Buffalo, SUNY) – Virtual presentation
Traditional fingerprint authentication requires the acquisition of data through touch-based specialized sensors. However, due to many hygienic concerns including the global spread of the COVID virus through contact with a surface has led to an increased interest in contactless fingerprint image acquisition methods. Matching fingerprints acquired using contactless imaging against contact-based images brings up the problem of performing cross modal fingerprint matching for identity verification. In this paper, we propose a cost-effective, highly accurate and secure end-to-end contactless fingerprint recognition solution. The proposed framework first segments the finger region from an image scan of the hand using a mobile phone camera. For this purpose, we developed a cross-platform mobile application for fingerprint enrollment, verification, and authentication keeping security, robustness, and accessibility in mind. The segmented finger images go through fingerprint enhancement to highlight discriminative ridge-based features. A novel deep convolutional network is proposed to learn a representation from the enhanced images based on the optimization of various losses. The proposed algorithms for each stage are evaluated on multiple publicly available contactless databases. Our matching accuracy and the associated security employed in the system establishes the strength of the proposed solution framework.
Assessment of Synthetically Generated Mated Samples from Single Fingerprint Samples Instances (10:20 AM – 10:40 AM)
Simon Kirchgasser (University of Salzburg), Christoph Kauba (University of Salzburg) and Andreas Uhl (University of Salzburg) – Virtual presentation
The availability of biometric data (here fingerprint samples) is a crucial requirement in all areas of biometrics. Due to recent changes in cross-border regulations (GDPR) sharing and accessing biometric sample data has become more difficult. An alternative way to facilitate a sufficient amount of test data is to synthetically generate biometric samples, which has its limitations. One of them is the generated data being not realistic enough and a more common one is that most free solutions are not able to generate mated samples, especially for fingerprints. In this work we propose a multi-level methodology to assess synthetically generated fingerprint data in terms of their similarity to real fingerprint samples. Furthermore, we present a generic approach to extend an existing synthetic fingerprint generator to be able to produce mated samples on the basis of single instances of non-mated ones which is then evaluated using the aforementioned multi-level methodology.