Invalid identity cards detection for EKYC system | |
| Author | Dinh Duy Khanh |
| Call Number | AIT Project no.PMDS-22-03 |
| Subject(s) | System safety Identification cards--Technological innovations Identity theft--Prevention |
| Note | A project study submitted in partial fulfillment of the requirements for the degree of Professional Master in Data Science and Artificial Intelligence Applications, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Project ; no. PMDS-22-03 |
| Abstract | By allowing customers to open accounts at home with eKYC, anti-forgery of identity documents (IDs) and portraits of document owners has become one of the top concerns of service providers. With only photos as input, there's a lot to check to make sure the IDs are valid. In this project, we present a solution to detect invalid IDs with 2 of the many tasks that need to be done: detecting edited faces on identity cards and identity documents taken from electronic devices for four types of common identity documents, Old identity card, Citizen identity card, Chip identity card, Vietnam Passport, on the system. By building different datasets for different tasks and types of identity documents and testing with advanced deep learning models, we have achieved over 98% accuracy on each model for known attack patterns while ensuring prediction speed at deployment under 0.1 seconds on Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz to ensure user experience. These models have been successfully deployed for VNPT eKYC products on VNPT's CPUs Cloud system with the number of requests reaching hundreds of millions. |
| Year | 2022 |
| Corresponding Series Added Entry | Asian Institute of Technology. Project ; no. PMDS-22-03 |
| Type | Project |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Professional Master in Data Science and Artificial Intelligence Applications (PMDS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Chutiporn Anutariya;Chaklam Silpasuwanchai; |
| Degree | Professional Master in Data Science and Artificial Intelligence Applications - Asian Institute of Technology, 2022 |