Skip to content
Open access

Performance Analysis of Deep and Hybrid Frameworks for Automated Image Splicing and Forgery Detection

Oct 2026 · International Journal of Modern Science and Research Technology · 0 citations · 3 references

Abstract

The exponential growth of digital images in cyberspace has raised concerns about cyber security, particularly in detecting tampering, forgery, and advanced manipulations. Conventional forensic methods are limited due to their reliance on manual inspection and predefined features, which makes them less effective against evolving cyber-attacks. This study introduces a predictive cyber security framework that combines digital forensic techniques with deep learning models to strengthen image protection. The approach employs convolutional neural networks (CNNs) and other deep architectures to learn high-level representations of image data, enabling the identification of threats such as steganography, splicing, deepfakes, and adversarial distortions. By embedding forensic principles into model training, the system enhances transparency and supports evidence traceability. This paper focuses on a predictive cyber security framework that integrates digital forensic techniques with deep learning models to improve the detection, interpretation, and prevention of digital image tampering and manipulation, thereby enhancing authenticity verification, transparency, and proactive defense in digital imaging.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.