Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …

Marabou 2.0: A Versatile Formal Analyzer of Neural Networks | SpringerLink Skip to main
content Advertisement SpringerLink Account Menu Find a journal Publish with us Track your …

Although neural networks are effective tools for processing information from image-based
sensors to produce control actions, their complex nature limits their use in safety-critical …

We consider the problem of certifying the robustness of deep neural networks against real-
world distribution shifts. To do so, we bridge the gap between hand-crafted specifications …

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

Fair representation learning transforms user data into a representation that ensures fairness
and utility regardless of the downstream application. However, learning individually fair …

Deep learning still has drawbacks in terms of trustworthiness, which describes a
comprehensible, fair, safe, and reliable method. To mitigate the potential risk of AI, clear …

Most real world applications require dealing with stochasticity like sensor noise or predictive
uncertainty, where formal specifications of desired behavior are inherently probabilistic …

The lack of trustworthiness is a major downside of deep learning. To mitigate the associated
risks clear obligations of deep learning models have been proposed via regulatory …

The objective of neural network (NN) robustness certification is to determine if a NN changes
its predictions when mutations are made to its inputs. While most certification research …