GANBA: Generative Adversarial Network for Biometric Anti-Spoofing

نویسندگان

چکیده

Automatic speaker verification (ASV) is a voice biometric technology whose security might be compromised by spoofing attacks. To increase the robustness against attacks, presentation attack detection (PAD) or anti-spoofing systems for detecting replay, text-to-speech and conversion-based attacks are being developed. However, it was recently shown that adversarial may seriously fool systems. Moreover, of whole system (ASV + PAD) this new type completely unexplored. In work, generative network (GANBA) proposed. GANBA has twofold basis: (1) jointly employs ASV losses to yield very damaging (2) trains PAD as discriminator in order make them more robust these types The proposed able generate which can complete system. Then, resulting discriminators used defense technique both original physical access (PA) logical (LA) scenarios ASVspoof 2019 database were employed carry out experiments. experimental results show quite effective, outperforming other techniques when applied white-box black-box setups. addition,

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Wasserstein Generative Adversarial Network

Recent advances in deep generative models give us new perspective on modeling highdimensional, nonlinear data distributions. Especially the GAN training can successfully produce sharp, realistic images. However, GAN sidesteps the use of traditional maximum likelihood learning and instead adopts an two-player game approach. This new training behaves very differently compared to ML learning. Ther...

متن کامل

Controllable Generative Adversarial Network

Although it is recently introduced, in last few years, generative adversarial network (GAN) has been shown many promising results to generate realistic samples. However, it is hardly able to control generated samples since input variables for a generator are from a random distribution. Some attempts have been made to control generated samples from GAN, but they have shown moderate results. Furt...

متن کامل

Multimodal Anti-spoofing in Biometric Recognition Systems

While multimodal biometric systems were commonly believed to be intrinsically more robust to spoof attacks than unimodal systems, recent results provided clear evidence that they can be evaded by spoofing a single biometric trait. This pointed out that also multimodal systems require specific anti-spoofing measures. In this chapter we introduce the issue of multimodal anti-spoofing, and give an...

متن کامل

GANGs: Generative Adversarial Network Games

Generative Adversarial Networks (GAN) have become one of the most successful frameworks for unsupervised generative modeling. As GANs are difficult to train much research has focused on this. However, very little of this research has directly exploited gametheoretic techniques.We introduce Generative Adversarial Network Games (GANGs), which explicitly model a finite zero-sum game between a gene...

متن کامل

CapsuleGAN: Generative Adversarial Capsule Network

We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adversarial network (GAN) setting, while modeling image data. We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates th...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Applied sciences

سال: 2022

ISSN: ['2076-3417']

DOI: https://doi.org/10.3390/app12031454