This academic article by Samantha Aziz and Oleg Komogortsev from Texas State University investigates the privacy risks associated with using eye movement biometrics for cross-platform identity linkage. The study reveals that a modern eye movement biometric model shows above-chance levels of biometric performance when linking user identities across one pair of devices, but not for others. The paper also discusses the impact that eye tracking signal quality has on the model’s ability to associate a subject’s identity between two different eye tracking devices. The findings contribute to the understanding of privacy risks for identity linkage across platforms.
Publication date: 13 Feb 2024
Project Page: https://arxiv.org/abs/2402.08655v1
Paper: https://arxiv.org/pdf/2402.08655
