Computational Assessment Model for Blind Medical Image Watermarking with Deep Learning

Blind watermarking is identified as one of the effective method of data hiding in image processing; however, existing literatures shows an adoption of sophisticated technique considering specific attacks. However, a potential gap is found where there is no report of resiliency of using blind watermarking towards resisting lethal threats. Therefore, this manuscript contributes towards offering a computational assessment model by constructing a lethal blind watermarking attacker model where a discrete orthogonal moments are extracted followed by dithering. The model is assessed on multiple modalities of standard medical image dataset as well as deep learning models. The outcome shows presented model accomplishes more than 45% of performance degradation from accuracy perspective. This outcome will offer clear guidelines of using deep learning models considering different medical image modalities to achieve better watermarking performance.