Abstract: Proposed are a computer-implemented method for accelerating convergence in the training of generative adversarial networks (GAN) to generate synthetic network traffic, and computer programs of same. The method allows the GAN network to ensure that the training converges in a limited time period less than the standard training period of existing GAN networks. The method allows results to be obtained in different use scenarios related to the generation and processing of network traffic data according to objectives such as the creations of arbitrary amounts of simulated data (a) with characteristics (statistics) similar to real datasets obtained from real network traffic, but (b) without including any part of any real dataset; diversity in the type of data to be created: IP traffic, network attacks, etc.; and the detection of changes in the network traffic patterns analysed and generated.

Abstract: A method for modelling a shape of data in a GAN comprising a generator agent (G) for generating synthetic data (110, 220) and a discriminator agent (D) for distinguishing between the generated synthetic data (120, 220) and real original data (110) that follow an arbitrary, continuous or discrete, distribution defined by a n-dimensional vector of input variables xi. The method, before generating output synthetic data (220), computes an Inverse Smirnov transformation fSi?1 for each of the n input variables xi and attaches an activation function (200) to the generator agent (G), wherein the activation function (200) is a n-dimensional vector faG formed by the computed Inverse Smirnov transformations, faG=(fS1?1, fS2?1, . . . , fSn?1). The GAN implementing the method generates the output synthetic data (220) using the activation function (200) which outputs synthetic data (220) with a distribution (420, 420?) whose shape is the same as the arbitraty distribution of the original data (110).