Artificial intelligence (AI) has been advancing at a fast pace and it is...
We study the problem of certifying the robustness of Bayesian neural net...
Neural network verification mainly focuses on local robustness propertie...
Linear Temporal Logic (LTL) is widely used to specify high-level objecti...
Probabilistic circuits (PCs) are a class of tractable probabilistic mode...
This report summarises the outcomes of a systematic literature search to...
Stochastic games are a convenient formalism for modelling systems that
c...
Distributional assumptions have been shown to be necessary for the robus...
Unsupervised representation learning leverages large unlabeled datasets ...
Solving a reinforcement learning (RL) problem poses two competing challe...
A fundamental problem in adversarial machine learning is to quantify how...
In many domains, worst-case guarantees on the performance (e.g., predict...
We consider the problem of certifying the individual fairness (IF) of
fe...
Bayesian structure learning allows one to capture uncertainty over the c...
Game-theoretic techniques and equilibria analysis facilitate the design ...
There is growing evidence that the classical notion of adversarial robus...
Design and control of autonomous systems that operate in uncertain or
ad...
Certifiers for neural networks have made great progress towards provable...
We consider the problem of computing reach-avoid probabilities for itera...
Robustness of decision rules to shifts in the data-generating process is...
We build on abduction-based explanations for ma-chine learning and devel...
Gaussian processes (GPs) enable principled computation of model uncertai...
We consider adversarial training of deep neural networks through the len...
Neural network NLP models are vulnerable to small modifications of the i...
Automated verification techniques for stochastic games allow formal reas...
Concurrent stochastic games (CSGs) are an ideal formalism for modelling
...
Many real world data analysis problems exhibit invariant structure, and
...
We study probabilistic safety for Bayesian Neural Networks (BNNs) under
...
Generalization across environments is critical to the successful applica...
Gaussian Processes (GPs) are widely employed in control and learning bec...
Deep neural network controllers for autonomous driving have recently
ben...
It is becoming increasingly important to understand the vulnerability of...
Research into safety in autonomous and semi-autonomous vehicles has, so ...
The widespread adoption of deep learning models places demands on their
...
Quantitative verification techniques have been developed for the formal
...
We consider Bayesian classification with Gaussian processes (GPs) and de...
We consider the setting of stochastic multiagent systems modelled as
sto...
Understanding the spatial arrangement and nature of real-world objects i...
We introduce a probabilistic robustness measure for Bayesian Neural Netw...
In the past few years, significant progress has been made on deep neural...
Probabilistic model checking for stochastic games enables formal verific...
A rise in popularity of Deep Neural Networks (DNNs), attributed to more
...
Bayesian inference and Gaussian processes are widely used in application...
Despite the improved accuracy of deep neural networks, the discovery of
...
Verifying correctness of deep neural networks (DNNs) is challenging. We ...
Concolic testing alternates between CONCrete program execution and symbO...
We consider probabilistic model checking for continuous-time Markov chai...
Deployment of deep neural networks (DNNs) in safety or security-critical...
Both experimental and computational biology is becoming increasingly
aut...
Despite the improved accuracy of deep neural networks, the discovery of
...