The ISC International Journal of Information Security

Abstract Image authenticity is a perennial issue with the evolution of advanced tampering techniques, particularly grid-aligned manipulations and spatial vulnerability-exploiting post-processing attacks. The paper presents a novel architecture for a neural network fusing Graph Neural Networks (GNNs), Convolutional Neural Networks (CNNs), and digital watermarking to detect tampering successfully and localise it. CNNs are trained on learning local spatial features, and an invisible low-dropout convolutional encoder places watermarks to ensure authenticity. GNNs address the inherent problem of modelling long-range structural relations for blind tampering pattern detection that is accurate. With a graph-based representation of image blocks, the framework learns complex spatial relations, which alleviates the rigid receptive field limitation. Extensive experiments on benchmark datasets confirm the framework’s superiority, achieving an F1-Score of 0.94 in tampering localisation, which significantly outperforms the 0.88 F1-Score of leading state-of-the-art methods. This approach creates a new standard for image integrity verification, offering an interpretable and scalable solution with far-reaching applications in digital content protection. 

Abstract Fragile watermarking is the task of embedding a watermark in a media (an image in this paper) such that even small changes, called tamper, can be detected or even recovered to prevent unauthorized alteration. A well-known category of spatial fragile watermarking methods is based on embedding the watermark in the least significant bits of the image to preserve the quality. In addition, Hamming code is a coding algorithm in communication that transmits the data-bits by augmenting some check-bits in order to exactly detect and recover single-bit modifications. This property is previously used to detect and perfectly recover the images modified by small tampers less than a quarter of the image in diameter. To achieve this goal, the Hamming code is applied on a distributed pixel, bits of which are gathered from sufficient far pixels in the image. It guarantees that such tampers can toggle at most one bit of each distributed Hamming code that is recoverable. It was the only guaranteed perfect reconstruction method of small tampers, based on our knowledge. In this paper, the method has been extended to support distortion in two bits of a Hamming code by use of common structures of distributed codes. It leads to guarantee recovery of tampers less than half of the image in width and height. According to the experimental results, the proposed method achieved better performance, in terms of recovering the tampered areas, in comparison to state-of-the-art.