The security of digital data has been attending more than past, spatially image data security. In this study, a hybrid image encryption method has been proposed based on genetic algorithm and chaos. Encryption process consists of three main steps: confusion phase, diffusion phase, and improvement phase using a genetic algorithm. At first, Chen’s chaotic map is used in the confusion phase to generate a scrambled image by shuffling plain-image pixels, and in the diffusion step, Logistic-Sine map alters those pixels gray-level values. It produces some of encrypted images which were considered as the initial population for the genetic algorithm. Then, by using the genetic algorithm, the encrypted images are optimized as much as possible. Finally, the best encrypted image is the final cipher image. The experimental results and several security analyses show that the proposed modified method provides an efficient scheme for image encryption and good robustness against frequent statistical and security attacks.