Existing techniques of watermarking make use of transform domain to have better robustness towards attacks. Here, we propose a novel learning based auto-encoder Convolutional Neural Network (CNN) for non-blind watermarking which outperforms the existing frequency domain techniques in terms of imperceptibility and robustness adding new dimension of usage of CNNs towards security. As these CNNs efficiently learn the features and represent the input at the output, they find applications in all the fields of science. Code book images of different size are generated using the proposed architecture and subjected to different attacks. Results of the proposed method are compared with state of the art methods at different noises and attacks such as Gaussian, speckle, compression effects, cropping, filtering, etc. The proposed scheme is validated against various possible attacks and its out-performance with state of the art methods is presented. Further, transfer learning capabilities of auto-encoder CNN for efficient way of learning new code book is presented. The inability of intruder towards retrieval of data without the knowledge of architecture and keys employed is also discussed. © 2016