148 citations · 265 across the 11 of their papers we have counts for
11 papers
ReMIA: a Powerful and Efficient Alternative to Membership Inference Attacks against Synthetic Data Generators
Davide Scassola, Andrea Coser, Sebastiano Saccani
Tabular data sharing under privacy constraints is increasingly important for research and collaboration. Synthetic data generators (SDGs) are a promising solution, but synthetic da…
A Sobering Look at Tabular Data Generation via Probabilistic Circuits
Davide Scassola, Dylan Ponsford, Adrián Javaloy +4
Tabular data is more challenging to generate than text and images, due to its heterogeneous features and much lower sample sizes. On this task, diffusion-based models are the curre…
Empirical Evaluation of Structured Synthetic Data Privacy Metrics: Novel experimental framework
Milton Nicolás Plasencia Palacios, Alexander Boudewijn, Sebastiano Saccani +6
Synthetic data generation is gaining traction as a privacy enhancing technology (PET). When properly generated, synthetic data preserve the analytic utility of real data while avoi…
Graph-Conditional Flow Matching for Relational Data Generation
Davide Scassola, Sebastiano Saccani, Luca Bortolussi
Data synthesis is gaining momentum as a privacy-enhancing technology. While single-table tabular data generation has seen considerable progress, current methods for multi-table dat…
Contrastive Learning-Based privacy metrics in Tabular Synthetic Datasets
Milton Nicolás Plasencia Palacios, Sebastiano Saccani, Gabriele Sgroi +2
Synthetic data has garnered attention as a Privacy Enhancing Technology (PET) in sectors such as healthcare and finance. When using synthetic data in practical applications, it is…
Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints
Davide Scassola, Sebastiano Saccani, Ginevra Carbone +1
Score-based diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific trai…
Generating Realistic Synthetic Relational Data through Graph Variational Autoencoders
Ciro Antonio Mami, Andrea Coser, Eric Medvet +7
Synthetic data generation has recently gained widespread attention as a more reliable alternative to traditional data anonymization. The involved methods are originally developed f…
Ground state and excitation properties of soft-core bosons
Tommaso Macri, Sebastiano Saccani, Fabio Cinti
We study the physics of soft-core bosons at zero temperature in two dimensions for a class of potentials that could be realised in experiments with Rydberg dressed Bose-Einstein co…
Minimum Energy Pathways via Quantum Monte Carlo
Sebastiano Saccani, Claudia Filippi, Saverio Moroni
We perform quantum Monte Carlo (QMC) calculations to determine minimum energy pathways of simple chemical reactions, and compare the computed geometries and reaction barriers with…
Excitation spectrum of a supersolid
Sebastiano Saccani, Saverio Moroni, Massimo Boninsegni
Conclusive experimental evidence of a supersolid phase in any known condensed matter system is presently lacking. On the other hand, a supersolid phase has been recently predicted…
Phase diagram of soft-core bosons in two dimensions
S. Saccani, S. Moroni, M. Boninsegni
The low temperature phase diagram of Bose soft disks in two dimensions is studied by numerical simulations. It is shown that a supersolid cluster phase exists, within a range of th…