Search

Recently, machine learning (ML) has been applying in almost all scientific fields to model and simulate the behaviour of complex systems. At the same time, the number of the proposed watermarking techniques have been increasing every year. Although most of the researchers in the watermarking and data hiding field put all their effort to compete each other to develop more efficient algorithm, the selection of the most efficient one is almost impossible for industries or software developers. In other words, comparison among all the watermarking techniques in order to select one watermarking technique would be cumbersome task. Moreover, the computer security is becoming more advanced which a single watermark technique cannot fulfil all the required criteria and there is a chance that an anti-watermarking is developed to remove the embedded watermark from the host data. This gap of knowledge to use the watermarking technology for a highly secure application is a real nightmare for the information security engineers and software designers. In this paper, two new approaches are proposed to train deep learning and shallow learning models based on the state-of-the-arts watermarking techniques. For these proposed approaches, several ML algorithms are applied to model various watermarked data, which are watermarked by different watermarking techniques in various spectrums and domains. An experimental setup is constructed based on several speeches, audios, images and videos beside the Amazon Sagemaker as ML modelling to implement the proposed approach. The experimental results show that apart from an overall effectiveness of the model, it would resolve some ambiguities by applying the proposed ML approach as a general watermarking workflow. [ABSTRACT FROM AUTHOR]