Formal verification under uncertainty
Being able to ensure that AI systems behave as intended is essential for their adoption in many areas. This series covers formal methods for the verification of safety, fairness, and other relevant properties of (probabilistic) ML systems. We document the progress in research domains such as neuro-symbolic verification, probabilistic model-checking, and weighted model integration.

All content in this series

Pill

Neuro Symbolic Verification of Deep Neural Networks

The neuro-symbolic approach to verification of neural networks uses reference networks to represent high level concepts. This allows the …

A picture of Faried
Formal Verification Under Uncertainty
Pill

Probabilistic Inference With Algebra and Logic Constraints

Hybrid probabilistic inference allows performing probabilistic inference with algebra and logic constraints. Recent advances with emphasis …

A picture of Faried
Formal Verification Under Uncertainty
Training

Probabilistic Model Checking with Storm

A 1-day workshop introducing the concept of probabilistic model checking and its applications with the Storm probabilistic model checker.

Other series in Safety and reliability in ML systems

Anomaly detection

Many industrial applications of automated decision-making involve the detection of anomalous behaviour. Precisely defining what this means is a complex problem hindered by strong class imbalances, lack of useful models or changing …

6 items

Robustness in ML

The robustness of a model is a measure of its stability with respect to perturbations of the input. We investigate and review recent developments in the field affecting the training, evaluation and deployment of ML systems.

6 items

Safety in learned controllers

Safety constraints for learned controllers with known dynamics.

1 item
Check all of our work