Avaliação de Modelos de Redes Neurais Recorrentes para Anonimização de Textos em Português

Currently, there are several approaches to provide anonymity on the Internet. However, one can still identify anonymous users through their writing style. With the advances in neural network and natural language processing research, the success of a classifier when accurately identify the author of a text is growing. On the other hand, new approaches that use recurrent neural networks for automatic generation of obfuscated texts have also arisen to fight anonymity adversaries. In this work, we evaluate two approaches that use neural networks to generate obfuscated texts. In our experiments, we compared the efficiency of both techniques when removing the stylistic attributes of a text and preserving its original semantics. Our results show a trade-off between the obfuscation level and the text semantics.