ABSTRACT
The progress made in deep learning has allowed the deployment of more powerful biometric authentication systems instead of traditional ones based on passwords or PIN codes. Facial recognition is widely used on smartphones to grant user access. However, advances in deep learning also improve methods for doctoring images and videos. A fraudulent user can use these methods to steal the identity of another person. It is very easy for impostors to present to the smartphone an image or video of the victim's face displayed on another screen. In this paper, we describe the security risks when a facial recognition system is attacked by presenting an image, a video or an interactive deepfake displayed on a screen. We also present a deep learning-based method to detect this kind of attack.
- Changsha, ZAO. 2019.Google Scholar
- I. Perov , « DeepFaceLab: A simple, flexible and extensible face swapping framework », ArXiv200505535 Cs Eess, 2020.Google Scholar
- A. Siarohin , « First Order Motion Model for Image Animation », 2019.Google Scholar
- J. Galbally , « Biometric Antispoofing Methods: A Survey in Face Recognition », IEEE Access, vol. 2, 2014.Google Scholar
- C. Lu and X. Tang, « Surpassing Human-Level Face Verification Performance on LFW with GaussianFace », ArXiv14043840, 2014.Google Scholar
- Y. Taigman , « DeepFace: Closing the Gap to Human-Level Performance in Face Verification », in Conference on Computer Vision and Pattern Recognition, USA, 2014.Google ScholarDigital Library
- G.G. Patil and R.K. Banyal, « A Dynamic Unconstrained Feature Matching Algorithm for Face Recognition », in Journal of Advances in Information Technology, 2020.Google Scholar
- J.A. Moreano and N.L. Palomino, « Global Facial Recognition Using Gabor Wavelet, Support Vector Machines and 3D Face Models », in Journal of Advances in Information Technology, 2020.Google ScholarCross Ref
- P. Easom-Mccaldin , « Towards Building A Facial Identification System Using Quantum Machine Learning Techniques », 2022.Google ScholarCross Ref
- Chandra ., « Application of "Face Recognition" Technology for Class Room Electronic Attendance Management System », in International Conference on ICT for Smart Society, 2020.Google Scholar
- Z. Luo and S.-T. Wu, « OLED Versus LCD: Who Wins? », 2015.Google Scholar
- H. Cao and A. C. Kot, « Identification of recaptured photographs on LCD screens », in International Conference on Acoustics, Speech and Signal Processing, USA, 2010.Google ScholarCross Ref
- H. Muammar and P. L. Dragotti, « An investigation into aliasing in images recaptured from an LCD monitor using a digital camera », in International Conference on Acoustics, Speech and Signal Processing, Canada, 2013.Google Scholar
- B. M. Adam Novoz, « Detecting Cyclostationarity in Re-Captured LCD Screens », J. Forensic Res., vol. 06, no 04, 2015.Google ScholarCross Ref
- Y. Ke , « Image Recapture Detection Using Multiple Features », Int. J. Multimed. Ubiquitous Eng., vol. 8, no 5, 2013.Google Scholar
- P. Yang , « Recapture Image Forensics Based on Laplacian Convolutional Neural Networks », in IWDW, 2017.Google Scholar
- H. Li , « Image Recapture Detection with Convolutional and Recurrent Neural Networks », Electron. Imaging, vol. 2017, no 7, 2017.Google Scholar
- E. Abraham, « Moiré Pattern Detection using Wavelet Decomposition and Convolutional Neural Network », in Symposium Series on Computational Intelligence (SSCI), India, 2018.Google Scholar
- X. Gao , « A Smart Phone Image Database for Single Image Recapture Detection », in Digital Watermarking, vol. 6526, 2011.Google Scholar
- S. Agarwal , « A Diverse Large-Scale Dataset for Evaluating Rebroadcast Attacks », in International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, 2018.Google Scholar
- T. Thongkamwitoon , « An Image Recapture Detection Algorithm Based on Learning Dictionaries of Edge Profiles », IEEE Trans. Inf. Forensics Secur., vol. 10, no 5, 2015.Google ScholarDigital Library
- T.-Y. Lin , « Microsoft COCO: Common Objects in Context », ArXiv14050312 Cs, 2015.Google Scholar
- M. Tan et Q. V. Le, « EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks », ArXiv190511946 Cs Stat, 2020.Google Scholar
Index Terms
- Recapture Detection to Fight Deep Identity Theft
Recommendations
Cybercrime, identity theft, and fraud: practicing safe internet - network security threats and vulnerabilities
InfoSecCD '06: Proceedings of the 3rd annual conference on Information security curriculum developmentComputer networks and computer systems are experiencing attacks and threats from many areas. Threats are also extended to include the individual user's computer assets and resources. Information will be presented on the categories of security and ...
Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing
Survey Paper and Regular PaperFace anti-spoofing aims to detect presentation attack to face recognition--based authentication systems. It has drawn growing attention due to the high security demand. The widely adopted CNN-based methods usually well recognize the spoofing faces when ...
Face spoofing detection under super-realistic 3D wax face attacks
Highlights- A new database with wax figure faces as super-realistic 3D face spoofing attacks.
AbstractFace spoofing attacks based on 3D face images have posed a severe security risk to face recognition systems. Despite the great effort made by the technical community in recent years, existing 3D face spoofing databases, mostly based on ...
Comments