In our first article related to the topic of DeepFakes, we have reminded our viewers on the dangers of these technologies, the various attempts from the industry to tackle the issue (including via a recent Kaggle competition launched by a consortium of major players such as Facebook) and our own idea to explore the topic further, by leveraging segmentation neural networks to not only recognize but also characterize the fakes, through the localization of modified areas. From

Deepfake comes with creative, fun but also more worrying applications. How good are machines at detecting them today ? Let's take a look.

A few weeks ago we published a blog post about adversarial examples in image classification. Today we share our own research on the topic.