3 citations · 3 across the 14 of their papers we have counts for
16 papers
Sound Probabilistic Safety Bounds for Large Language Models
Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani +1
We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new applicati…
Incremental Data-Driven Policy Synthesis via Game Abstractions
Irmak Sağlam, Mahdi Nazeri, Alessandro Abate +2
We address the synthesis of control policies for unknown discrete-time stochastic dynamical systems to satisfy temporal logic objectives. We present a data-driven, abstraction-base…
Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics
Mahdi Nazeri, Thom Badings, Anne-Kathrin Schmuck +2
We study the automated abstraction-based synthesis of correct-by-construction control policies for stochastic dynamical systems with unknown dynamics. Our approach is to learn an a…
Probabilistic Alternating Simulations for Policy Synthesis in Uncertain Stochastic Dynamical Systems
Thom Badings, Alessandro Abate
A classical approach to formal policy synthesis in stochastic dynamical systems is to construct a finite-state abstraction, often represented as a Markov decision process (MDP). Th…
Data-Driven Yet Formal Policy Synthesis for Stochastic Nonlinear Dynamical Systems
Mahdi Nazeri, Thom Badings, Sadegh Soudjani +1
The automated synthesis of control policies for stochastic dynamical systems presents significant challenges. A standard approach is to construct a finite-state abstraction of the…
Temporal Logic Control for Nonlinear Stochastic Systems Under Unknown Disturbances
Ibon Gracia, Luca Laurenti, Manuel Mazo +2
In this paper, we present a novel framework to synthesize robust strategies for discrete-time nonlinear systems with random disturbances that are unknown, against temporal logic sp…
Risk-Averse Certification of Bayesian Neural Networks
Xiyue Zhang, Zifan Wang, Yulong Gao +3
In light of the inherently complex and dynamic nature of real-world environments, incorporating risk measures is crucial for the robustness evaluation of deep learning models. In t…
A data-driven approach for safety quantification of non-linear stochastic systems with unknown additive noise distribution
Frederik Baymler Mathiesen, Licio Romao, Simeon C. Calvert +2
In this paper, we present a novel data-driven approach to quantify safety for non-linear, discrete-time stochastic systems with unknown noise distribution. We define safety as the…
Data-driven memory-dependent abstractions of dynamical systems via a Cantor-Kantorovich metric
Adrien Banse, Licio Romao, Alessandro Abate +1
Abstractions of dynamical systems enable their verification and the design of feedback controllers using simpler, usually discrete, models. In this paper, we propose a data-driven…
Data-driven Interval MDP for Robust Control Synthesis
Rudi Coppola, Andrea Peruffo, Licio Romao +2
The abstraction of dynamical systems is a powerful tool that enables the design of feedback controllers using a correct-by-design framework. We investigate a novel scheme to obtain…
A Stability-Based Abstraction Framework for Reach-Avoid Control of Stochastic Dynamical Systems with Unknown Noise Distributions
Thom Badings, Licio Romao, Alessandro Abate +1
Finite-state abstractions are widely studied for the automated synthesis of correct-by-construction controllers for stochastic dynamical systems. However, existing abstraction meth…
Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers
Alexandros E. Tzikas, Licio Romao, Mert Pilanci +2
Many machine learning applications require operating on a spatially distributed dataset. Despite technological advances, privacy considerations and communication constraints may pr…
Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Rohan Mitta, Hosein Hasanbeig, Jun Wang +3
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during le…
Learning Robust Policies for Uncertain Parametric Markov Decision Processes
Luke Rickard, Alessandro Abate, Kostas Margellos
Synthesising verifiably correct controllers for dynamical systems is crucial for safety-critical problems. To achieve this, it is important to account for uncertainty in a robust m…
Correct-by-Construction Control for Stochastic and Uncertain Dynamical Models via Formal Abstractions
Thom Badings, Nils Jansen, Licio Romao +1
Automated synthesis of correct-by-construction controllers for autonomous systems is crucial for their deployment in safety-critical scenarios. Such autonomous systems are naturall…
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…