Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)

Enhancing Security in Deepfake Detection Systems through Hybrid Ecdsa (Ecc and Dsa) Cryptographic Technique

Authors
N. Thilagavathi1, *, S. Shriram2, M. Sai Poobbathy3, S. Sharan4
1Professor, Department of Information Technology, Sri Manakula Vinayagar Engineering College, Puducherry, India
2Bachelor of Technology, Department of Information Technology, Sri Manakula Vinayagar Engineering College, Puducherry, India
3Bachelor of Technology, Department of Information Technology, Sri Manakula Vinayagar Engineering College, Puducherry, India
4Bachelor of Technology, Department of Information Technology, Sri Manakula Vinayagar Engineering College, Puducherry, India
*Corresponding author. Email: thilagavthi@smvec.ac.in
Corresponding Author
N. Thilagavathi
Available Online 31 March 2026.
DOI
10.2991/978-94-6239-616-6_123How to use a DOI?
Keywords
Deepfake detection; ResNet-50; CNN; ECDSA; GANs; cybersecurity; digital forensics
Abstract

The creation of hyper-realistic deepfakes using the Generative Adversarial Networks (GANs) is rapidly becoming one of the most severe threats to privacy, digital trust, and security, so much so that they give rise to massive misinformation, impersonation, and manipulation. The paper reviews the development of deepfake detection technologies and proposes a hybrid framework that combines deep learning with cryptographic authentication to achieve accurate detection and secure verification of digital media. The detection layer uses a ResNet-50-based CNN to detect subtle pixel-level anomalies, mismatched facial features, and motion inconsistencies in altered media. To guarantee integrity and accountability, we use the elliptic curve digital signature algorithm (ECDSA) to issue lightweight tamper-proof digital signatures. By merging these two levels, the system not only increases the accuracy of deepfake detection but also provides a trusted verification means that can be used for social media monitoring, digital forensics, and national security. The survey sheds light on current challenges, including dataset bias and computational constraints, also outlining a path for the future to create scalable, secure, and trustworthy deepfake detection systems.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
Series
Advances in Intelligent Systems Research
Publication Date
31 March 2026
ISBN
978-94-6239-616-6
ISSN
1951-6851
DOI
10.2991/978-94-6239-616-6_123How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - N. Thilagavathi
AU  - S. Shriram
AU  - M. Sai Poobbathy
AU  - S. Sharan
PY  - 2026
DA  - 2026/03/31
TI  - Enhancing Security in Deepfake Detection Systems through Hybrid Ecdsa (Ecc and Dsa) Cryptographic Technique
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1727
EP  - 1757
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_123
DO  - 10.2991/978-94-6239-616-6_123
ID  - Thilagavathi2026
ER  -