In this paper we proposed an adaptive secure client-side Look-Up-Table (LUT) based digital audio watermarking, which adaptively choose an optimal embedding strength for individual segment of host signal according to specific properties of each segment. It is clear that different segments of host signal featured different characteristics, so using the embedding strength adaptively would definitely improve the inaudibility of watermarking while maintaining the robustness level nearly unchanged. Consequently, the proposed approach features the combination properties of both security property derived from Secure Client-side Embedding and better robustness and inaudibility from the adaptive embedding strength of individual segment. Simulation results show that the watermark in this scheme can survive robustly after being subjected to various common audio attacks, such as filtering, resample and so on. © 2011 IEEE.