共性特征学习的高泛化伪造指纹检测  

High-generalization spoofing fingerprint detection based on commonality feature learning

作　　者：袁程胜 徐震宇[1,2] 向凌云[3] 付章杰[1,2] 夏志华 Yuan Chengsheng;Xu Zhenyu;Xiang Lingyun;Fu Zhangjie;Xia Zhihua(School of Computer Science,School of Cyber Science and Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;Engineering Research Center of Digital Forensics of Ministry of Education,Nanjing University of Information Science and Technology,Nanjing 210044,China;College of Computer and Communication Engineering,Changsha University of Science and Technology,Changsha 410114,China;College of Cyber Security,Jinan University,Guangzhou 510632,China)

机构地区：[1]南京信息工程大学计算机学院、网络空间安全学院,南京210044 [2]南京信息工程大学数字取证教育部工程研究中心,南京210044 [3]长沙理工大学计算机与通信工程学院,长沙410114 [4]暨南大学网络空间安全学院,广州510632

出　　处：《中国图象图形学报》2024年第9期2780-2792,共13页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62102189,62122032);江苏省自然科学基金项目(BK20200807);国家社会科学基金项目(2022-SKJJ-C-082);国防科技大学科研项目(JS21-4,ZK21-43)。

摘　　要：目的指纹识别技术已大规模应用于人们的日常生活中,如身份鉴定、指纹支付与考勤等。然而,最新研究表明这些系统极易遭受伪造指纹的欺骗攻击,因此在使用指纹认证用户身份前,鉴别待测指纹的真伪至关重要。伪造指纹的制作材料具有多样性,现有工作忽视了不同材料伪造指纹之间数据分布的关联性,致使跨材料检测泛化性普遍较低。因此,本文通过分析不同材料伪造指纹数据间的分布关联性,挖掘不同伪造指纹间的材料域不变伪造特征,提出了一种基于共性特征学习的高泛化伪造指纹检测方法。方法首先,为了表征和学习不同材料伪造指纹间的特征,设计了一种多尺度伪造特征提取器(multi-scale spoofing feature extractor,MSFE),包含一个多尺度空间通道(multi-scale spatial-channel,MSC)注意力模块,以学习真假指纹类间的细粒度差异特征。然后,为了进一步分析不同材料伪造指纹数据间的分布关联性,又构造了一种共性伪造特征提取器(common spoofing feature extractor,CSFE),在MSFE先验知识的引导下进行多任务的材料域不变伪造特征学习。最后,设计一个材料鉴别器对学习到的共性伪造特征进行约束,同时构建一个自适应联合优化损失模块来平衡多个模块在训练过程中的损失权重,以进一步提高面对未知材料伪造指纹检测时的泛化性。结果在两个公开的指纹数据集(LivDet(liveness detection com⁃petition)2017和LivDet2019)上进行了跨材料测试,实验结果表明所提算法相较对比工作,ACE(average classification error)降低了1.34%,TDR(true detection rate)提高了1.43%,表现出较高的泛化性。结论本文算法在ACE和TDR方面均取得优异性能。此外,当面对未知材料的伪造指纹检测时,同样表现出较强的泛化性。Objective The realm of our daily lives has witnessed the ubiquitous integration of fingerprint recognition technology in domains,such as authorized identification,fingerprint-based payments,and access control systems.However,recent studies have revealed the vulnerability of these systems to spoofing fingerprint attacks.Attackers can deceive authen⁃tication systems by imitating fingerprints using artificial materials.Thus,the authenticity of fingerprint under scrutiny must be ascertained prior to its use to authenticate the user's identity.The development of a spoofing fingerprint detection tech⁃nology has attracted extensive attention from the academia and industry.The creation of spoofing fingerprints involve the use of diverse materials.The present research disregards the correlation of data distribution among spoofing fingerprints crafted from various materials,which consequently leads to limited generalization in cross-material detection.Hence,a high-generalization spoofing fingerprint detection method based on commonality feature learning is proposed through the analysis of the distribution correlation among counterfeit fingerprint data originating from diverse materials and the explora⁃tion of invariant forgery features within the material domain of distinct counterfeit fingerprints.Method First,to character⁃ize and learn the features of spoofing fingerprints obtained using various materials,a multiscale spoofing feature extractor(MFSE)is designed,and it includes a multiscale spatial-channel attention module to allow the MFSE to pay more attention to fine-grained differences between live and fake fingerprints and improve the capability of the network to learn spoofing fea⁃tures.Then,a common spoofing feature extractor(CSFE)is constructed for further analysis of the distribution correlation between spoofing fingerprint data of different materials and extraction of common spoofing features between spoofing finger⁃prints made from various materials.Under the guidance of prior knowledge on MFSE,CSFE

关 键 词：伪造指纹检测 材料域不变伪造特征 注意力 共性特征学习 泛化性 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]