51 citations · 67 across the 8 of their papers we have counts for
8 papers
Out-of-Distribution Detection using Counterfactual Distance
Maria Stoica, Francesco Leofante, Alessio Lomuscio
Accurate and explainable out-of-distribution (OOD) detection is required to use machine learning systems safely. Previous work has shown that feature distance to decision boundarie…
Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
Junqi Jiang, Jianglin Lan, Francesco Leofante +2
Counterfactual Explanations (CEs) have received increasing interest as a major methodology for explaining neural network classifiers. Usually, CEs for an input-output pair are defi…
Formalising the Robustness of Counterfactual Explanations for Neural Networks
Junqi Jiang, Francesco Leofante, Antonio Rago +1
The use of counterfactual explanations (CFXs) is an increasingly popular explanation strategy for machine learning models. However, recent studies have shown that these explanation…
Robot Swarms as Hybrid Systems: Modelling and Verification
Stefan Schupp, Francesco Leofante, Leander Behr +2
A swarm robotic system consists of a team of robots performing cooperative tasks without any centralized coordination. In principle, swarms enable flexible and scalable solutions;…
Verification of Neural Networks: Enhancing Scalability through Pruning
Dario Guidotti, Francesco Leofante, Luca Pulina +1
Verification of deep neural networks has witnessed a recent surge of interest, fueled by success stories in diverse domains and by abreast concerns about safety and security in env…
SMarTplan: a Task Planner for Smart Factories
Arthur Bit-Monnot, Francesco Leofante, Luca Pulina +2
Smart factories are on the verge of becoming the new industrial paradigm, wherein optimization permeates all aspects of production, from concept generation to sales. To fully pursu…
Automated Verification of Neural Networks: Advances, Challenges and Perspectives
Francesco Leofante, Nina Narodytska, Luca Pulina +1
Neural networks are one of the most investigated and widely used techniques in Machine Learning. In spite of their success, they still find limited application in safety- and secur…
On the Synthesis of Guaranteed-Quality Plans for Robot Fleets in Logistics Scenarios via Optimization Modulo Theories
Francesco Leofante, Erika Ábrahám, Tim Niemueller +2
In manufacturing, the increasing involvement of autonomous robots in production processes poses new challenges on the production management. In this paper we report on the usage of…