27 citations · 152 across the 28 of their papers we have counts for
34 papers
Probabilistic Reach-Avoid for Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +3
Model-based reinforcement learning seeks to simultaneously learn the dynamics of an unknown stochastic environment and synthesise an optimal policy for acting in it. Ensuring the s…
Adversarial Robustness Certification for Bayesian Neural Networks
Matthew Wicker, Andrea Patane, Luca Laurenti +1
We study the problem of certifying the robustness of Bayesian neural networks (BNNs) to adversarial input perturbations. Given a compact set of input points $T \subseteq \mathbb{R}…
BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming
Steven Adams, Andrea Patane, Morteza Lahijanian +1
In this paper, we introduce BNN-DP, an efficient algorithmic framework for analysis of adversarial robustness of Bayesian Neural Networks (BNNs). Given a compact set of input point…
Individual Fairness in Bayesian Neural Networks
Alice Doherty, Matthew Wicker, Luca Laurenti +1
We study Individual Fairness (IF) for Bayesian neural networks (BNNs). Specifically, we consider the --individual fairness notion, which requires that, for any pair of input…
Inner approximations of stochastic programs for data-driven stochastic barrier function design
Frederik Baymler Mathiesen, Licio Romao, Simeon C. Calvert +2
This paper proposes a new framework to compute finite-horizon safety guarantees for discrete-time piece-wise affine systems with stochastic noise of unknown distributions. The appr…
Interval Markov Decision Processes with Continuous Action-Spaces
Giannis Delimpaltadakis, Morteza Lahijanian, Manuel Mazo +1
Interval Markov Decision Processes (IMDPs) are finite-state uncertain Markov models, where the transition probabilities belong to intervals. Recently, there has been a surge of res…
On the Robustness of Bayesian Neural Networks to Adversarial Attacks
Luca Bortolussi, Ginevra Carbone, Luca Laurenti +3
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical a…
Safety Certification for Stochastic Systems via Neural Barrier Functions
Frederik Baymler Mathiesen, Simeon Calvert, Luca Laurenti
Providing non-trivial certificates of safety for non-linear stochastic systems is an important open problem that limits the wider adoption of autonomous systems in safety-critical…
Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions
Rayan Mazouz, Karan Muvvala, Akash Ratheesh +2
Neural Networks (NNs) have been successfully employed to represent the state evolution of complex dynamical systems. Such models, referred to as NN dynamic models (NNDMs), use iter…
Individual Fairness Guarantees for Neural Networks
Elias Benussi, Andrea Patane, Matthew Wicker +2
We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs). In particular, we work with the --IF formulation, which, given a NN…
Formal Control Synthesis for Stochastic Neural Network Dynamic Models
Steven Adams, Morteza Lahijanian, Luca Laurenti
Neural networks (NNs) are emerging as powerful tools to represent the dynamics of control systems with complicated physics or black-box components. Due to complexity of NNs, howeve…
Formal Analysis of the Sampling Behaviour of Stochastic Event-Triggered Control
Giannis Delimpaltadakis, Luca Laurenti, Manuel Mazo
Analyzing Event-Triggered Control's (ETC) sampling behaviour is of paramount importance, as it enables formal assessment of its sampling performance and prediction of its sampling…
Formal Verification of Unknown Dynamical Systems via Gaussian Process Regression
John Skovbekk, Luca Laurenti, Eric Frew +1
Leveraging autonomous systems in safety-critical scenarios requires verifying their behaviors in the presence of uncertainties and black-box components that influence the system dy…
Synergistic Offline-Online Control Synthesis via Local Gaussian Process Regression
John Jackson, Luca Laurenti, Eric Frew +1
Autonomous systems often have complex and possibly unknown dynamics due to, e.g., black-box components. This leads to unpredictable behaviors and makes control design with performa…
Certification of Iterative Predictions in Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +3
We consider the problem of computing reach-avoid probabilities for iterative predictions made with Bayesian neural network (BNN) models. Specifically, we leverage bound propagation…
A Language for Modeling And Optimizing Experimental Biological Protocols
Luca Cardelli, Marta Kwiatkowska, Luca Laurenti
Automation is becoming ubiquitous in all laboratory activities, leading towards precisely defined and codified laboratory protocols. However, the integration between laboratory pro…
Adversarial Robustness Guarantees for Gaussian Processes
Andrea Patane, Arno Blaas, Luca Laurenti +3
Gaussian processes (GPs) enable principled computation of model uncertainty, making them attractive for safety-critical applications. Such scenarios demand that GP decisions are no…
Strategy Synthesis for Partially-known Switched Stochastic Systems
John Jackson, Luca Laurenti, Eric Frew +1
We present a data-driven framework for strategy synthesis for partially-known switched stochastic systems. The properties of the system are specified using linear temporal logic (L…
Abstracting the Sampling Behaviour of Stochastic Linear Periodic Event-Triggered Control Systems
Giannis Delimpaltadakis, Luca Laurenti, Manuel Mazo
Recently, there have been efforts towards understanding the sampling behaviour of event-triggered control (ETC), for obtaining metrics on its sampling performance and predicting it…
Bayesian Inference with Certifiable Adversarial Robustness
Matthew Wicker, Luca Laurenti, Andrea Patane +3
We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Netwo…
Assessing Robustness of Text Classification through Maximal Safe Radius Computation
Emanuele La Malfa, Min Wu, Luca Laurenti +3
Neural network NLP models are vulnerable to small modifications of the input that maintain the original meaning but result in a different prediction. In this paper, we focus on rob…
Probabilistic Safety for Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +1
We study probabilistic safety for Bayesian Neural Networks (BNNs) under adversarial input perturbations. Given a compact set of input points, , we study t…
Safety Verification of Unknown Dynamical Systems via Gaussian Process Regression
John Jackson, Luca Laurenti, Eric Frew +1
The deployment of autonomous systems that operate in unstructured environments necessitates algorithms to verify their safety. This can be challenging due to, e.g., black-box compo…
Robustness of Bayesian Neural Networks to Gradient-Based Attacks
Ginevra Carbone, Matthew Wicker, Luca Laurenti +3
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical a…