Embedding graphic content in multimedia through steganography is a useful and fast practice to hide information. However, detecting the use of this technique is complex and sometimes unsuccessful because variations are not visually perceptible. This article proposes the use of a binary classification model based on artificial neural networks to detect the presence of LSB steganography on monochromatic still images of 256x256 and 8 bits, based on the Standford Genome Project. The steganograms were generated by varying the payload from 0.1 to 0.5 to obtain image pairs of carriers and steganograms. For each steganogram, the following features were extracted from image histograms: kurtosis, skewness, standard deviation, range, median, harmonic mean, Hjorth mobility, and complexity. The results show that the classifier reaches a 91.45% accuracy in detecting LSB steganography when learning from all payloads, as well as a 96.78% individual classification accuracy in the best case with a payload of 0.5.

* Autor a quien debe ser dirigida la correspondenciaRecibido Jul. 6, 2017; Aceptado Sep. 1, 2017; Versión final Nov. 7, 2017, Publicado Feb. 2018 Resumen Este artículo presenta el análisis sistémico de los componentes de la seguridad utilizando los lenguajes de la dinámica de sistemas tales como la prosa, el diagrama de influencias, de flujo-nivel, las ecuaciones y los comportamientos. La dinámica de sistemas permite el análisis de la complejidad de los elementos de la seguridad mediante la caracterización de los ciclos de realimentación presentes para el entendimiento, explicación y pronóstico de la misma. Se muestra la utilidad del modelo propuesto a través de la simulación de escenarios hipotéticos, permitiendo con ello medir la seguridad de la información. Palabras clave: dinámica de sistemas; seguridad informática; seguridad de la información; ciberseguridad Analysis of the Components of Security from a Systemic System Dynamics Perspective AbstractThis article presents the systemic analysis of the components of security with the use of the languages of systems dynamics such as the prose, influence diagram, flow-level, equations and behaviors. Systems dynamics allows the analysis of the complexity of security's elements through the characterization of the existing feedback cycles, for the perception, explanation and prediction of security. The usefulness of the proposed model is shown through the simulation of hypothetical scenarios, allowing in this way measuring information security.