In this paper, a dynamic stochastic resonance (DSR) technique is used for blind watermark extraction in discrete cosine transform (DCT) domain. The watermark embedding has been done on mid-band DCT coefficients. DSR has been used to improve the robustness of the extraction algorithm by utilizing the degradation introduced during attacks. DSR is an iterative process that tunes the coefficients of the possibly attacked watermarked image so that the effect of noise is suppressed and hidden information is enhanced. Resilience of this technique has been tested in the presence of various attacks. An adaptive optimization procedure has been adopted for the selection of bistable parameters to achieve maximum correlation coefficient under minimum computational complexity. Using the proposed technique, robust extraction of watermark is obtained without trading-off with visual quality of the watermarked image. When compared with the plain DCT-based technique, DSR-based technique has been found to give remarkable performance. © 2013 Published by Elsevier Ltd. All rights reserved.