Graph Fourier Transform Based Audio Zero-Watermarking

The frequent exchange of multimedia information in thepresent era projects an increasing demand for copyright protection. In this work, we propose a novel audio zero-watermarking technology based on graph Fourier transform enhancing the robustness with respect to approach, combined shift operator is used construct signal, upon which analysis performed. selected maximum absolute coefficients representing characteristics segment are then encoded into feature binary sequence using K-means algorithm. Finally, resultant XOR-ed watermark realize embedding zero-watermarking. experimental studies show that proposed approach performs more effectively resisting common or synchronization attacks than existing state-of-the-art methods.