AI security blog

In this first post of a longer series around Gandalf, we want to highlight some of the inner workings of Gandalf: what exactly is happening at each level, and how is Gandalf getting stronger?

As we all know from machine learning 101, you should split your dataset into three parts: the training, validation, and test set. You train your models on the training set. You choose your hyperparameters by selecting the best model from the validation set. Finally, you look at your accuracy (F1 score, ROC curve...) on the test set. And voilà, you’ve just achieved XYZ% accuracy.

Deep-dive into advanced comparison methods beyond standard performance metrics to build computer vision models that consistently perform over the long term.

We are excited to announce the release of our first integration with FiftyOne by Voxel51. This integration makes it possible to benefit from FiftyOne's powerful visualization features to dig into the insights generated by Lakera's MLTest. Read on to learn how you can benefit from this.

We have released an implementation of OpenAI’s CLIP model that completely removes the need for PyTorch, enabling you to quickly and seamlessly install this fantastic model in production and even possibly on edge devices.

Will my system work if image quality starts to drop significantly? If my system works at a given occlusion level, how much stronger can occlusion get before the system starts to underperform? I have faced such issues repeatedly in the past, all related to an overarching question: How robust is my model and when does it break?