Fatima Abu Siryeh*, Hussein Alrammahi, Abdullahi Abdu İbrahim
CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5021-5046, 2025, DOI:10.32604/cmc.2025.065206
- 30 July 2025
Abstract Biometric template protection is essential for finger-based authentication systems, as template tampering and adversarial attacks threaten the security. This paper proposes a DCT-based fragile watermarking scheme incorporating AI-based tamper detection to improve the integrity and robustness of finger authentication. The system was tested against NIST SD4 and Anguli fingerprint datasets, wherein 10,000 watermarked fingerprints were employed for training. The designed approach recorded a tamper detection rate of 98.3%, performing 3–6% better than current DCT, SVD, and DWT-based watermarking approaches. The false positive rate (≤1.2%) and false negative rate (≤1.5%) were much lower compared to previous… More >