RCF-QTM: A Robust Framework for Image Tampering Detection and Reconstruction

In response to the vulnerabilities found in current image security technologies, this paper introduces a novel security framework that integrates the Quasi Threshold Model(QTM) and Rubik's Cube Filtering (RCF). This method enhances image protection by redistributing pixel information across a multi-dimensional space through block-based segmentation, thus increasing its resilience against hostile attacks. The Quasi Threshold Model employs dynamic threshold adjustments to adaptively detect and reconstruct tampered areas. This adaptive mechanism enables RCF and QTM to provide robust encryption, decryption, and greater interpretability, surpassing traditional models like CNNs and Deep-CNN s, often compromised by adversarial manipulations and regional limitations. This research study demonstrates the proposed framework achieves a reconstruction accuracy of 98%, significantly exceeding the performance of CNN sand Deep-CNNs, with PSNR values of 38.75% and 48.52%, respectively. This paper details the framework's architecture and comparative performance evaluation and discusses the implications of its enhanced security features for high-risk environments.