Improving the performance of data hiding by designing three samples-based smoothing in audio

The internet is widely applied to facilitate the transferring process of data as a means of communication. Some of this transferred message has confidential information and must be protected. One of the techniques to protect is data hiding. It uses carrier media as a cover to hide information inside it, one of which is audio. However, there are some problems in the use of audio, namely the limited capacity and sound quality after data insertion. In this paper, we address these problems by interpolating the audio samples using Modification Lagrange Interpolation (MLI) and exploring Reduce Difference Expansion (RDE) for embedded the secret. Next, samples are smoothed to improve the quality based on three sampling signal points of the stego audio. The testing of proposed method is carried out on fifteen mono audio data sets from various genres the covers and ten files as confidential information data with various file sizes. The results show that using the proposed methods, the performance increases that the average quality of each audio genre raises by about 4dB and able to increase the capacity of message data that can be hidden by 20%.