Palmprint False Acceptance Attack with a Generative Adversarial Network (GAN)
Palmprint False Acceptance Attack with a Generative Adversarial Network (GAN)
复制标题
DOI：
10.3390/app10238547
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Fei Wang;L. Leng;A. Teoh;Jun Chu
中科院分区：
文献类型：
--
作者：
Fei Wang;L. Leng;A. Teoh;Jun Chu
目前，基于生物特征的身份认证被广泛应用于多媒体系统中，然而，生物特征系统容易受到图像级的冒充攻击。重建攻击(RA)和呈现攻击(PA)是两种典型的图像级攻击。在RA中，重建的图像由于存在明显的伪造物，往往自然度不足，因此其伪造物很容易被机器或人检测到。PA要求真实用户的原始图像，而这些图像在实践中很难获得，并在欺骗性载体上伪造假生物识别图像。在本文中，我们提出了一种针对掌纹生物特征的虚假接受攻击(FAA)，它克服了RA和PA的上述问题。FAA不需要真实的用户图像，只需生成对抗性网络生成的自然度较高的合成图像即可启动。作为一个案例研究，我们论证了FAA相对于基于编码的掌纹生物识别系统的可行性。为了进一步提高FAA的效率，我们使用了一种聚类的方法来选择不同的伪图像，以增强所使用的伪图像的多样性，从而减少了攻击次数。实验结果表明了FAA算法的成功率和有效性。
Biometric-based authentication is widely deployed on multimedia systems currently; however, biometric systems are vulnerable to image-level attacks for impersonation. Reconstruction attack (RA) and presentation attack (PA) are two typical instances for image-level attacks. In RA, the reconstructed images often have insufficient naturalness due to the presence of remarkable counterfeit appearance, thus their forgeries can be easily detected by machine or human. The PA requires genuine users’ original images, which are difficult to acquire in practice and to counterfeit fake biometric images on spoofing carriers. In this paper, we develop false acceptance attack (FAA) for a palmprint biometric, which overcomes the aforementioned problems of RA and PA. FAA does not require genuine users’ images, and it can be launched simply with the synthetic images with high naturalness, which are generated by the generative adversarial networks. As a case study, we demonstrate the feasibility of FAA against coding-based palmprint biometric systems. To further improve the efficiency of FAA, we employ a clustering method to select diverse fake images in order to enhance the diversity of the fake images used, so the number of attack times is reduced. Our experimental results show the success rate and effectiveness of the FAA.