SynID: Passport Synthetic Dataset for Presentation Attack Detection
This addresses the problem of detecting fraudulent ID documents in remote verification systems, which is crucial for security in contexts like remote work and online transactions, but it is incremental as it focuses on dataset creation rather than a new detection method.
The paper tackles the challenge of limited real ID documents for training Presentation Attack Detection (PAD) systems by proposing a new synthetic passport dataset generated from a hybrid method combining synthetic data and open-access information, resulting in realistic training and testing images based on ICAO requirements.
The demand for Presentation Attack Detection (PAD) to identify fraudulent ID documents in remote verification systems has significantly risen in recent years. This increase is driven by several factors, including the rise of remote work, online purchasing, migration, and advancements in synthetic images. Additionally, we have noticed a surge in the number of attacks aimed at the enrolment process. Training a PAD to detect fake ID documents is very challenging because of the limited number of ID documents available due to privacy concerns. This work proposes a new passport dataset generated from a hybrid method that combines synthetic data and open-access information using the ICAO requirement to obtain realistic training and testing images.