In this paper, we propose the use of a Convolutional Neural Network (CNN) to identify offensive tweets, as well as the type and target of the offense. We use an end-to-end model (i.e., no preprocessing) and fine-tune pre-trained embeddings (FastText) during training for learning words’ representation. We compare the proposed CNN model to a baseline model, such as Linear Regression, and several neural models. The results show that CNN outperforms other models, and stands as a simple but strong baseline in comparison to other systems submitted to the Shared Task.