Formal verification of neural networks is critical for their safe adoption in real-world
applications. However, designing a precise and scalable verifier which can handle different …

The right to be forgotten calls for efficient machine unlearning techniques that make trained
machine learning models forget a cohort of data. The combination of training and unlearning …

A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …

AI applications powered by deep learning inference are increasingly run natively on edge
devices to provide better interactive user experience. This often necessitates fitting a model …

We present DeepT, a novel method for certifying Transformer networks based on abstract
interpretation. The key idea behind DeepT is our new Multi-norm Zonotope abstract domain …

The use of deep 3D point cloud models in safety-critical applications, such as autonomous
driving, dictates the need to certify the robustness of these models to real-world …

Deep neural networks are vulnerable to input deformations in the form of vector fields of
pixel displacements and to other parameterized geometric deformations eg translations …

In contrast with ad-hoc methods for eXplainable Artificial Intelligence (XAI), formal
explainability offers important guarantees of rigor. However, formal explainability is hindered …

Building models that comply with the invariances inherent to different domains, such as
invariance under translation or rotation, is a key aspect of applying machine learning to real …

The formal safety analysis of automated driving vehicles poses unique challenges due to
their dynamic operating conditions and significant complexity. This paper presents a case …