计算机科学 ›› 2021, Vol. 48 ›› Issue (2): 330-336.doi: 10.11896/jsjkx.200100020

• 信息安全 • 上一篇    

基于深度特征增广的跨域小样本人脸欺诈检测算法

孙文赟1, 金忠2, 赵海涛3, 陈昌盛1   

  1. 1 深圳大学电子与信息工程学院深圳市媒体信息内容安全重点实验室 广东 深圳518060
    2 南京理工大学计算机科学与工程学院高维信息智能感知与系统教育部重点实验室 南京210094
    3 华东理工大学信息科学与工程学院 上海200237
  • 收稿日期:2020-01-03 修回日期:2020-04-23 出版日期:2021-02-15 发布日期:2021-02-04
  • 通讯作者: 陈昌盛(cschen@szu.edu.cn)
  • 作者简介:wenyunsun@szu.edu.cn
  • 基金资助:
    国家自然科学基金(61902250,61702340,61872188);国家重点基础研究发展计划(2014CB349303);中国博士后科学基金面上项目(2018M643183);广东省自然科学基金(2017A030310382);深圳市基础研究自由探索项目(JCYJ20180305124550725,827/000213)

Cross-domain Few-shot Face Spoofing Detection Method Based on Deep Feature Augmentation

SUN Wen-yun1, JIN Zhong2, ZHAO Hai-tao3, CHEN Chang-sheng1   

  1. 1 Shenzhen Key Laboratory of Media Security, College of Electronics, Information Engineering, Shenzhen University, Shenzhen, Guangdong 518060, China
    2 School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China
    3 School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China
  • Received:2020-01-03 Revised:2020-04-23 Online:2021-02-15 Published:2021-02-04
  • About author:SUN Wen-yun,born in 1987,Ph.D.His main research interests include deep learning and facial image analysis.
    CEHN Chang-sheng,born in 1986,Ph.D,lecturer,postgraduate supervisor,is a member of China Compu-ter Federation.His main research interests include 2D barcode,pattern recognition,machine learning and information security.
  • Supported by:
    The National Natural Science Foundation of China(61902250,61702340,61872188),National Basic Research Program of China(2014CB349303),China Postdoctoral Science Foundation(2018M643183),Natural Science Foundation of Guangdong Province(2017A030310382) and ShenzhenBasic Research and Free Exploration Project(JCYJ20180305124550725,827/000213).

摘要: 随着人脸识别技术的发展,人脸欺诈攻击已经成为一项实际的安全问题,人脸欺诈检测算法用于及早发现该类攻击,保护系统安全。文中将一种经典域自适应算法扩展到深度神经网络中,首先定义了基于深度特征增广的域自适应层,提出了一种基于深度特征增广的跨域小样本人脸欺诈检测算法。该算法在已有的基于全卷积神经网络的人脸欺诈检测深度神经网络的中部嵌入域自适应层将卷积特征图增广,来适配源域和目标域的差异,随后根据增广后的特征图进行像素级分类,最后将像素级概率图从空间上融合为帧级决策。文中在CASIA-FASD,Replay-Attack和OULU-NPU 3个数据集和6个常见测评协议(2个CASIA-FASD与Replay-Attack跨库协议和4个OULU-NPU标准协议)下进行实验,验证了算法在不同背景、不同攻击设备、不同相机等跨域情况下的性能。实验表明,基准FCN人脸欺诈检测算法已经能够达到较好的性能,在此基础上,借助小样本目标域数据学习域自适应模型,可进一步显著提升性能,将错误率减半(CASIA-FASD训练+Replay-Attack测试的HTER指标从27.31%降至11.23%,Replay-Attack训练+CASIA-FASD测试的HTER指标从37.33%降至21.83%,OULU-NPU标准协议IV的ACER指标从9.45%降至5.56%),实验结果验证了基于深度特征增广的跨域小样本人脸欺诈检测算法的有效性。

关键词: 模式识别, 人脸欺诈检测, 人脸图像分析, 深度学习, 系统安全

Abstract: The face recognition technology is improving rapidly these days.One the other side,the face presentation attack has become a practical security problem.To protect the system,face presentation attack detection methods are employed for detecting such attacks in advance.This paper extends a classic domain adaptation method to the deep neural network scenario,defines a feature augmentation-based domain adaptation layer,proposes a cross-domain few-shot face presentation attack detection method based on deep feature augmentation.This method is based on the existing method based on Fully Convolutional Network and improves the existing method by embedding a domain adaptation layer in the middle of the network.The new layer augments the feature maps,adapts the difference between the source and target domains.Then,a pixel-level probability map is predicted based on the augmented the feature maps.Finally,the prediction map is fused to a frame-level decision.Experiments are conducted on the CASIA-FASD,Replay-Attack and OULU-NPU datasets.Six commonly used protocols including the cross-dataset protocols between CASIA-FASD and Replay-Attack,the standard protocols of the OULU-NPU dataset are followed.The training and test data are cross different backgrounds,presentation attack instruments and cameras.The experiment results show that the baseline method,the Fully Convolutional Networkbased face presentation attack detection method has already achieved state-of-the-art performance.The performance can be further improved by learning the domain adaptation model on small-sample data in the target domain.The proposed method can halve the error rate by introducing domain adaptation (train on CASIA-FASD and test on Replay-Attack:decreased from 27.31% to 11.23%,train on Replay-Attack and test on CASIA-FASD:decreased from 37.33% to 21.83%,OULU-NPU's standard protocol IV:decreased from 9.45% to 5.56%).This confirms the effectiveness of the proposed method.

Key words: Deep learning, Face spoofing detection, Facial image analysis, Pattern recognition, System security

中图分类号: 

  • TP311
[1] MENOTTI D,CHIACHIA G,PINTO A,et al.Deep representations for iris,face,and fingerprint spoofing detection[J].IEEE Transactions on Information Forensics and Security,2015,10(4):864-879.
[2] REHMAN Y A U,PO L M,LIU M.Deep learning for face anti-spoofing:An end-to-end approach[C]//Signal Processing:Algorithms,Architectures,Arrangements,and Applications.IEEE,2017:195-200.
[3] NAGPAL C,DUBEY S R.A Performance Evaluation of Convolutional Neural Networks for Face Anti Spoofing[C]//International Joint Conference on Neural Networks.IEEE,2018.
[4] LIU Y,JOURABLOO A,LIU X.Learning deep models for face anti-spoofing:Binary or auxiliary supervision[C]//Conference on Computer Vision and Pattern Recognition.IEEE,2018:389-398.
[5] ATOUM Y,LIU Y,JOURABLOO A,et al.Face anti-spoofing using patch and depth-based CNNs[C]//International Joint Conference on Biometrics.IEEE,2017:319-328.
[6] GEORGE A,MARCEL S E B.Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection[C]//International Conference on Biometrics.IEEE,2019.
[7] SUN W,SONG Y,CHEN C,et al.Face Spoofing Detectionbased on Local Ternary Label Supervision in Fully Convolutio-nal Network[J].IEEE Transactions on Information Forensics and Security,2020,15:3181-3196.
[8] JOURABLOO A,LIU Y,LIU X.Face de-spoofing:Anti-spoo-fing via noise modeling[C]//European Conference on Computer Vision.IEEE,2018:290-306.
[9] YANG X,LUO W,BAO L,et al.Face Anti-Spoofing ModelMatters,So Does Data[C]//Conference on Computer Vision and Pattern Recognition.IEEE,2019:3507-3516.
[10] BOULKENAFET Z,KOMULAINEN J,HADID A.Face Spoofing Detection Using Colour Texture Analysis[J].IEEE Transactions on Information Forensics and Security,2016,11(8):1818-1830.
[11] BOULKENAFET Z,KOMULAINEN J,HADID A.Face anti-spoofing based on color texture analysis[C]//Conference on Ima-ge Processing.IEEE,2015:2636-2640.
[12] NIKISINS O,MOHAMMADI A,ANJOS A E,et al.On effectiveness of anomaly detection approaches against unseen presentation attacks in face anti-spoofing[C]//International Confe-rence on Biometrics.IEEE,2018:75-81.
[13] WEN D,HAN H,JAIN A K.Face spoof detection with image distortion analysis[J].IEEE Transactions on Information Forensics and Security,2015,10(4):746-761.
[14] GALBALLY J,MARCEL S E B,FIERREZ J.Image quality assessment for fake biometric detection:Application to iris,fingerprint,and face recognition[J].IEEE Transactions on Image Processing,2014,23(2):710-724.
[15] PATEL K,HAN H,JAIN A K.Secure face unlock:Spoof detection on smartphones[J].IEEE Transactions on Information Forensics and Security,2016,11(10):2268-2283.
[16] KUMAR S,SINGH S,KUMAR J.A comparative study on face spoofing attacks[C]//International Conference on Computing,Communication and Automation.IEEE,2017:1104-1108.
[17] MUAMMAR H,DRAGOTTI P L.An investigation into alia-sing in images recaptured from an LCD monitor using a digital camera[C]//International Conference on Acoustics,Speech and Signal Processing.IEEE,2013:2242-2246.
[18] GARCIA D C,DE QUEIROZ R L.Face-spoofing 2D-detection based on moire-pattern analysis[J].IEEE Transactions on Information Forensics and Security,2015,10(4):778-786.
[19] NI R,ZHAO Y,ZHAI X.Recaptured Images Forensics Based On Color Moments and DCT Coefficients Features[J].Journal of Information Hiding and Multimedia Signal Processing,2015,6(2):323-333.
[20] MÄÄTTÄ J,HADID A,PIETIKÄINEN M.Face spoofing detection from single images using micro-texture analysis[C]//International Joint Conference on Biometrics.IEEE,2011.
[21] PATEL K,HAN H,JAIN A K,et al.Live face video vs.spoof face video:Use of moire patterns to detect replay video attacks[C]//International Conference on Biometrics.IEEE,2015:98-105.
[22] LI H,LI W,CAO H,et al.Unsupervised domain adaptation for face anti-spoofing[J].IEEE Transactions on Information Forensics and Security,2018,13(7):1794-1809.
[23] ARASHLOO S R,KITTLER J,CHRISTMAS W.Face spoofing detection based on multiple descriptor fusion using multiscale dynamic binarized statistical image features[J].IEEE Transactions on Information Forensics and Security,2015,10(11):2396-2407.
[24] YANG J,LEI Z,YI D,et al.Person-specific face antispoofing with subject domain adaptation[J].IEEE Transactions on Information Forensics and Security,2015,10(4):797-809.
[25] DE FREITAS PEREIRA T,KOMULAINEN J,ANJOS A E,et al.Face liveness detection using dynamic texture[J].EURASIP Journal on Image and Video Processing,2014,2014(1):2.
[26] SIMONYAN K,ZISSERMAN A.Two-stream convolutionalnetworks for action recognition in videos[C]//International Conference on Neural Information Processing Systems.NeurIPS Foundation,2014:568-576.
[27] SUN W,ZHAO H,JIN Z.3D convolutional neural networks for facial expression classification[C]//Asian Conference on Computer Vision.AFCV,2016:528-543.
[28] SUN W,ZHAO H,JIN Z.A facial expression recognition method based on ensemble of 3D convolutional neural networks[J].Neural Computing and Applications,2019,31(7):2795-2812.
[29] YIN W,MING Y,TIAN L.A face anti-spoofing method based on optical flow field[C]//International Conference on Signal Processing.IEEE,2016:1333-1337.
[30] PINTO A,PEDRINI H,SCHWARTZ W R,et al.Face spoofing detection through visual codebooks of spectral temporal cubes[J].IEEE Transactions on Image Processing,2015,24(12):4726-4740.
[31] DE MARSICO M,NAPPI M,RICCIO D,et al.Moving facespoofing detection via 3D projective invariants[C]//Internatio-nal Conference on Biometrics.IEEE,2012:73-78.
[32] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[33] DAUMÉ H I.Frustratingly easy domain adaptation[J].arXiv:0907.1815,2009.
[34] BOUSMALIS K,TRIGEORGIS G,SILBERMAN N,et al.Domain separation networks[C]//International Conference on Neural Information Processing Systems.NeurIPS Foundation,2016:343-351.
[35] ZHANG Z,YAN J,LIU S,et al.A face antispoofing database with diverse attacks[C]//IAPR International Conference on Biometrics.IEEE,2012:26-31.
[36] CHINGOVSKA I,ANJOS A E,MARCEL S E B.On the Effectiveness of Local Binary Patterns in Face Anti-spoofing[C]//International Conference of Biometrics.IEEE,2012.
[37] BOULKENAFET Z,KOMULAINEN J,LI L,et al.OULU-NPU:A mobile face presentation attack database with real-world variations[C]//International Conference on Automatic Face & Gesture Recognition.IEEE,2017.
[38] HE H,GARCIA E A.Learning from imbalanced data[J].IEEE Transactions on Knowledge & Data Engineering,2008(9):1263-1284.
[39] DE FREITAS PEREIRA T,ANJOS A E,DE MARTINO J E M,et al.Can face anti-spoofing countermeasures work in a real world scenario?[C]//International Conference on Biometrics.IEEE,2013.
[40] BHARADWAJ S,DHAMECHA T I,VATSA M,et al.Computationally efficient face spoofing detection with motion magnification[C]//Conference on Computer Vision and Pattern Recognition.IEEE,2013:105-110.
[41] YANG J,LEI Z,LI S Z.Learn convolutional neural network for face anti-spoofing[J].arXiv:1408.5601,2014.
[42] BOULKENAFET Z,KOMULAINEN J,AKHTAR Z,et al.A competition on generalized software-based face presentation attack detection in mobile scenarios[C]//International Joint Conference on Biometrics.IEEE,2017:688-696.
[43] LIN C,LIAO Z,ZHOU P,et al.Live Face Verification withMultiple Instantialized Local Homographic Parameterization[C]//International Joint Conference on Artificial Intelligence.IJCAI Organization,2018:814-820.
[1] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[2] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[3] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[4] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[5] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[6] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[7] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[8] 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木.
中文预训练模型研究进展
Advances in Chinese Pre-training Models
计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018
[9] 周慧, 施皓晨, 屠要峰, 黄圣君.
基于主动采样的深度鲁棒神经网络学习
Robust Deep Neural Network Learning Based on Active Sampling
计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044
[10] 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫.
小样本雷达辐射源识别的深度学习方法综述
Survey of Deep Learning for Radar Emitter Identification Based on Small Sample
计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138
[11] 胡艳羽, 赵龙, 董祥军.
一种用于癌症分类的两阶段深度特征选择提取算法
Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification
计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092
[12] 程成, 降爱莲.
基于多路径特征提取的实时语义分割方法
Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction
计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[13] 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋.
改进Faster R-CNN的光学遥感飞机目标检测
Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN
计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
[14] 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤.
不同数据增强方法对模型识别精度的影响
Influence of Different Data Augmentation Methods on Model Recognition Accuracy
计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210
[15] 毛典辉, 黄晖煜, 赵爽.
符合监管合规性的自动合成新闻检测方法研究
Study on Automatic Synthetic News Detection Method Complying with Regulatory Compliance
计算机科学, 2022, 49(6A): 523-530. https://doi.org/10.11896/jsjkx.210300083
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!