Privacy-Preserving Biometric Verification With Handwritten Random Digit String

2025-01-14

IEEE Transactions on Pattern Analysis and Machine Intelligence

AI Summary

Handwriting-based biometrics pose significant privacy risks due to the potential leakage of personally identifiable information. Method: This paper proposes a privacy-preserving authentication framework based on handwritten Random Digit Strings (RDS), where users write arbitrary digit sequences—eliminating the need to expose sensitive personal data. We introduce the first RDS verification paradigm and construct HRDS4BV, the first publicly available online RDS dataset. We design PAVENet—a Pattern Attentive VErification Network—and a Discriminative Pattern Mining (DPM) module to model dynamic handwriting features at fine granularity. Crucially, we identify and leverage users’ spontaneous forgery behaviors as an intrinsic defense mechanism against adversarial attacks. Results: Evaluated on HRDS4BV, our method outperforms state-of-the-art approaches, achieving high accuracy (EER < 2.1%), strong privacy guarantees, and real-time robust authentication—demonstrating the feasibility and efficacy of the RDS paradigm.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Large-scale security measurements

Abstract

Handwriting verification has stood as a steadfast identity authentication method for decades. However, this technique risks potential privacy breaches due to the inclusion of personal information in handwritten biometrics such as signatures. To address this concern, we propose using the Random Digit String (RDS) for privacy-preserving handwriting verification. This approach allows users to authenticate themselves by writing an arbitrary digit sequence, effectively ensuring privacy protection. To evaluate the effectiveness of RDS, we construct a new HRDS4BV dataset composed of online naturally handwritten RDS. Unlike conventional handwriting, RDS encompasses unconstrained and variable content, posing significant challenges for modeling consistent personal writing style. To surmount this, we propose the Pattern Attentive VErification Network (PAVENet), along with a Discriminative Pattern Mining (DPM) module. DPM adaptively enhances the recognition of consistent and discriminative writing patterns, thus refining handwriting style representation. Through comprehensive evaluations, we scrutinize the applicability of online RDS verification and showcase a pronounced outperformance of our model over existing methods. Furthermore, we discover a noteworthy forgery phenomenon that deviates from prior findings and discuss its positive impact in countering malicious impostor attacks. Substantially, our work underscores the feasibility of privacy-preserving biometric verification and propels the prospects of its broader acceptance and application.

Problem

• Address privacy risks in handwriting biometric verification.
• Propose Random Digit String for secure authentication.
• Develop PAVENet and DPM for style recognition.

Innovation

• Random Digit String for privacy-preserving verification
• PAVENet with DPM for handwriting style recognition
• HRDS4BV dataset for evaluating RDS effectiveness