Abstract
The in-air signature verification system has garnered attention due to its flexibility, friendliness, security, high efficiency, remote accessibility, and contactless usage patterns. However, with the advancement of machine learning, computers can now learn and imitate many things through artificial intelligence. This technology, referred to as “deepfake”, has been used to create fake signatures, raising concerns about the security of the in-air signature verification system. Consequently, research on in-air signature verification technology against deepfakes has become an urgent need. The current challenges are: (1) Most research on in-air signature verification at this stage focuses on human forgery, with a lack of high-performance verification systems for deepfake in-air signatures. (2) Due to the long sequence and small amount of data, there is a lack of good generation methods for in-air signature generation tasks. To address these challenges, this paper proposes an improved in-air feature data model based on the GLNLSTM autoencoder. The signature samples generated by this model are more authentic than the baseline model. Additionally, we introduce an in-air signature verification model based on a two-channel model. The signature semantic feature extraction module of this model uses one-dimensional CNN and bidirectional LSTM to extract dynamic time features. This model achieves the best results in both deepfake verification and artificial forgery signature verification tasks on the SCUT-MMSIG-AIR database.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Korshunov, P, Marcel, S.: Subjective and objective evaluation of deepfake videos. In: Proceedings of the 46th International Conference on Acoustics, Speech and Signal Processing, pp. 2510-2514. IEEE (2021)
Wijethunga, R.L.M.A.P.C., et al.: Deepfake audio verification: a deep learning based solution for group conversations. In: Proceedings of the 2nd International Conference on Advancements in Computing, pp. 192-197. IEEE (2020)
Han, B., et al.: Fighting fake news: two stream model for deepfake verification via learnable SRM. IEEE Trans. Biometrics Behav. Identity Sci. 3(3), 320-331 (2021)
Zhang, Z., Liu, X., Cui, Y.: Multi-phase offline signature verification system using deep convolutional generative adversarial models. In: Proceedings of the 9th International Symposium on Computational Intelligence and Design, pp. 103-107. IEEE (2016)
Manongga, D.H.F., Nataliani, Y., Wellem, T.H.: Anti-counterfeit handwritten signature via DCGAN with SGPD model. In: Proceedings of the 7th International Conference on Applied System Innovation, pp. 79-84. IEEE (2021)
Yoon, J, Jarrett, D, van der Schaar, M.: Time-series generative adversarial networks. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp. 5508-5518. ACM (2019)
Li, Xiaomin, et al.: Tts-gan: A transformer-based time-series generative adversarial model. In: Proceedings of the International Conference on Artificial Intelligence in Medicine. pp. 133-143. Springer (2022). https://doi.org/10.1007/978-3-031-09342-5_13
Tolosana, R., et al.: DeepWriteSYN: On-line handwriting synthesis via deep short-term representations. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, pp. 600-608. AAAI (2021)
Zhang, X., Xue, Y.: A novel gan-based synthesis model for in-air handwritten words. Sensors 20(22), 1-18 (2020)
Lu, X., Fang, Y., Wu, Q., Zhao, J., Kang, W.: A novel multiple distances based dynamic time warping method for online signature verification. In: Zhou, J., et al. (eds.) CCBR 2018. LNCS, vol. 10996, pp. 645–652. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-97909-0_68
Tang, L., Kang, W., Fang, Y.: Information divergence-based matching strategy for online signature verification. IEEE Trans. Inform. Forensics Sec. 13(4), 861-873 (2017)
Katagiri, M., Sugimura, T.: Personal authentication by free space signing with video capture. In: Proceedings of the 5th Asian Conference on Computer Vision, pp. 350-355. Springer (2002)
Ngoc Diep, N., Pham, C., Minh Phuong, T.: SigVer3D: accelerometer based verification of 3-D signatures on mobile devices. In: Nguyen, V.-H., Le, A.-C., Huynh, V.-N. (eds.) Knowledge and Systems Engineering. AISC, vol. 326, pp. 353–365. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-11680-8_28
Bailador, G., et al.: Analysis of pattern recognition techniques for in-air signature biometrics. Pattern Recog. 44(10-11), 2468-2478 (2011)
Sajid, H., Cheung Sen-ching, S.: VSig: Hand-gestured signature recognition and authentication with wearable camera. In: Proceedings of the 7th International Workshop on Information Forensics and Security, pp. 1-6. IEEE (2015)
Fang, Y., et al.: A novel video-based system for in-air signature verification. Comput. Electr. Eng. 57, 1-14 (2017)
Behera, S.K., Dogra, D.P., Roy, P.P.: Fast recognition and verification of 3D air signatures using convex hulls. Expert Syst. Appli. 100, 106-119 (2018)
De Luisa, L., et al.: In-air 3D dynamic signature recognition using haptic devices. In Proceedings of the 9th International Workshop on Biometrics and Forensics, pp. 106-119. IEEE (2021)
Guerra-Segura, E., Ortega-Pérez, A., Travieso, C.M.: In-air signature verification system using leap motion. Expert Syst. Appli. 165, 113797 (2021)
Li, G., Zhang, L., Sato, H.: In-air signature authentication using smartwatch motion sensors. In: Proceedings of the 45th International Computer Software and Applications Conference, pp. 386-395. IEEE (2021)
Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv: 1607. 06450 (2016)
Zeineldeen, M., et al.: Layer-normalized LSTM for hybrid-HMM and end-to-end ASR. In: Proceedings of the 45th International Conference on Acoustics, Speech and Signal Processing, pp. 7679-7683. IEEE (2020)
Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4353-4361. IEEE (2015)
Li, C., et al.: DeepHSV: User-independent offline signature verification using two-channel CNN. In: Proceedings of the 15th International Conference on Document Analysis and Recognition, pp. 161-171. IEEE (2019)
Lu, X., Fang, Y., Kang, W., Wang, Z., Feng, D.D.: SCUT-MMSIG: a multimodal online signature database. In: Zhou, J., et al. (eds.) CCBR 2017. LNCS, vol. 10568, pp. 729–738. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-69923-3_78
Acknowledgements
This study is supported by the Project for Science and Technology of Inner Mongolia Autonomous Region under Grant 2019GG281, the Natural Science Foundation of Inner Mongolia Autonomous Region under Grant 2019ZD14, the Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region under Grant NJYT-20-A05, the fund of supporting the reform and development of local universities (Disciplinary Construction) and construction project of “Inner Mongolia Science and Technology Achievement Transfer and Transformation Demonstration Zone, University Collaborative Innovation Base, and University Entrepreneurship Training Base” (Supercomputing Power Project: 21300-231510).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, H., Wei, H., Wang, Y. (2024). Deepfake In-Air Signature Verification via Two-Channel Model. In: Barney Smith, E.H., Liwicki, M., Peng, L. (eds) Document Analysis and Recognition - ICDAR 2024. ICDAR 2024. Lecture Notes in Computer Science, vol 14805. Springer, Cham. https://doi.org/10.1007/978-3-031-70536-6_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-70536-6_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-70535-9
Online ISBN: 978-3-031-70536-6
eBook Packages: Computer ScienceComputer Science (R0)