Improve the Spoofing Resistance of Multimodal Verification with Representation-Based Measures
Recently,the security of multimodal verification has become a growing concern since many fusion systems have been known to be easily deceived by partial spoof attacks,i.e.only a subset of modalities is spoofed.In this paper,we verify such a vulnerability and propose to use two representationbased measures to close this gap.Firstly,we use the collaborative representation fidelity with non-target subjects to measure the affinity of a query sample to the claimed client.We further consider sparse coding as a competing comparison among the client and the non-target subjects,and hence explore two sparsitybased measures for recognition.Last,we select the representation-based measure,and assemble its score and the affinity score of each modality to train a support vector machine classifier.Our experimental results on a chimeric multimodal database with face and ear traits demonstrate that in both regular verification and partial spoof attacks,the proposed method significantly outperforms the well-known fusion methods with conventional measure.
Multimodal verification Spoof attacks Representation-based measure Support vector machine
Zengxi Huang Zhen-Hua Feng Josef Kittler Yiguang Liu
School of Computer and Software Engineering,Xihua University,Chengdu,China Centre for Vision,Speech and Signal Processing,University of Surrey,Guildford,UK College of Computer Science,Sichuan University,Chengdu,China
国际会议
广州
英文
388-399
2018-11-23（万方平台首次上网日期，不代表论文的发表时间）