Analisis Keamanan Sistem Biometrik terhadap Ancaman Deepfake : Studi Kasus Lonjakan 3.000% Fraud Incidents Periode 2023-2024

Osewa Pallyama Sultan Khadir; Asep Saeppani; Esa Firmansyah; Beben Sutara

doi:10.61132/merkurius.v4i4.1318

Authors

Osewa Pallyama Sultan Khadir Universitas Sebelas April Sumedang
Asep Saeppani Universitas Sebelas April Sumedang
Esa Firmansyah Universitas Sebelas April Sumedang
Beben Sutara Universitas Sebelas April Sumedang

DOI:

https://doi.org/10.61132/merkurius.v4i4.1318

Keywords:

Biometrics, Cybersecurity, Deepfake, Face Recognition, Security Framework

Abstract

The rapid advancement of deepfake technology powered by Generative AI has created a critical security threat to biometric authentication systems, particularly face recognition and voice recognition. Global reports from 2023–2024 indicate a dramatic 3,000% increase in deepfake-enabled identity fraud, emphasizing the urgent need for stronger biometric security measures. This study aims to analyze key vulnerabilities in biometric systems against deepfake attacks, evaluate the effectiveness of existing detection techniques, and develop a layered biometric security framework as a mitigation solution. The research employs a Systematic Literature Review (SLR) of scientific publications and industry reports from 2016–2025, complemented by Lite Expert Validation to assess the feasibility of the proposed framework. The findings reveal that most biometric systems remain vulnerable to advanced face swap, voice cloning, and liveness detection bypass attacks. Detection methods based on frequency–spatial analysis and multi-modal deepfake detection are identified as the most effective, although they require strong operational integration. This study introduces the Biometric Deepfake Security Framework, which incorporates technical, procedural, and adaptive security controls to enhance biometric resilience against digital identity manipulation. The proposed framework is expected to provide practical guidance for organizations relying on biometric authentication to strengthen protection against evolving deepfake threats.

References

Ayeswarya, S., & Singh, R. (2024). Vulnerabilities of biometric authentication systems against deepfake-based attacks. International Journal of Information Security, 23(1), 45–60. https://doi.org/10.1007/s10207-023-00745-2

Bator, R. J., Bryan, A. D., & Schultz, P. W. (2011). Who gives a hoot?: Intercept surveys of litterers and disposers. Environment and Behavior, 43(3), 295–315. https://doi.org/10.1177/0013916509356884

Biometrics Institute. (2024). Biometrics trends and threats report 2024. Biometrics Institute.

CNN International. (2024). Deepfake video scam costs engineering firm Arup $25 million. CNN International. https://edition.cnn.com

Federal Bureau of Investigation. (2024). Internet crime report 2023. FBI.

Gao, X., Zhao, H., & Wang, Y. (2025). Multi-modal deepfake detection for secure biometric authentication systems. IEEE Transactions on Information Forensics and Security, 20, 1–15. https://doi.org/10.1109/TIFS.2024.3456789

He, Z., Liu, J., & Chen, C. (2024). Realistic deepfake generation and its impact on biometric verification systems. Pattern Recognition, 149, 110185. https://doi.org/10.1016/j.patcog.2023.110185

iProov Ltd. (2024). Threat intelligence report: Face biometric attacks. iProov.

International Organization for Standardization. (2023). ISO/IEC 30107-3: Biometric presentation attack detection. ISO.

ISACA. (2024). Digital trust and identity security framework. ISACA.

Luan, S., Zhang, K., & Li, J. (2024). Frequency–spatial feature analysis for deepfake face detection. Expert Systems with Applications, 235, 121176. https://doi.org/10.1016/j.eswa.2023.121176

Livingstone, S. (2019). Audiences in an age of datafication: Critical questions for media research. Television & New Media, 20(2), 170–183. https://doi.org/10.1177/1527476418811118

NIST. (2020). Digital identity guidelines (SP 800-63B). National Institute of Standards and Technology.

NIST. (2024). Artificial intelligence risk management framework. National Institute of Standards and Technology.

Qureshi, A., Malik, A., & Khan, S. (2024). Deepfake-enabled identity fraud: Threat landscape and mitigation strategies. Computers & Security, 133, 103345. https://doi.org/10.1016/j.cose.2023.103345

Rahmawati, D., & Nugroho, Y. (2022). Digital literacy and cybersecurity awareness among Indonesian internet users. Journal of Information Security Research, 11(2), 89–102.

Safa, N. S., & Von Solms, R. (2016). An information security knowledge sharing model in organizations. Computers in Human Behavior, 57, 442–451. https://doi.org/10.1016/j.chb.2015.12.037

Salahdine, F., & Kaabouch, N. (2019). Social engineering attacks: A survey. Future Internet, 11(4), 89. https://doi.org/10.3390/fi11040089

Štitilis, D., Pakutinskas, P., & Laurinaitis, M. (2023). Legal and technical challenges of biometric identification in the age of deepfakes. Computer Law & Security Review, 50, 105780. https://doi.org/10.1016/j.clsr.2023.105780

Sugiyono. (2021). Metode penelitian kuantitatif, kualitatif, dan R&D. Bandung: Alfabeta.

Sumsub. (2024). Identity fraud report 2024. Sumsub.

Tolosana, R., Romero, A., Galbally, J., & Fierrez, J. (2020). Deepfakes and beyond: A survey of face manipulation and fake detection. Information Fusion, 64, 131–148. https://doi.org/10.1016/j.inffus.2020.06.014

Zhao, H., Li, X., & Gao, X. (2023). Adaptive authentication strategies for biometric systems against synthetic media attacks. IEEE Security & Privacy, 21(6), 42–51. https://doi.org/10.1109/MSEC.2023.3287654