Search Results

Documents authored by Dolcetti, Greta

Artifact
Software
DOI: 10.4230/artifacts.26386
FaVeX

Authors: Alessandro De Palma, Greta Dolcetti, and Caterina Urban

Abstract
Cite as

Alessandro De Palma, Greta Dolcetti, Caterina Urban. FaVeX (Software, Source Code). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-26386,
   title = {{FaVeX}}, 
   author = {De Palma, Alessandro and Dolcetti, Greta and Urban, Caterina},
   note = {Software (visited on 2026-06-25)},
   url = {https://github.com/alessandrodepalma/favex},
   doi = {10.4230/artifacts.26386},
}
Document
DOI: 10.4230/LIPIcs.ECOOP.2026.3
Faster Verified Explanations for Neural Networks

Authors: Alessandro De Palma, Greta Dolcetti, and Caterina Urban

Published in: LIPIcs, Volume 372, 40th European Conference on Object-Oriented Programming (ECOOP 2026)

Abstract
Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations. FaVeX accelerates the computation by dynamically combining batch and sequential processing of input features, and by reusing information from previous queries, both when proving invariances with respect to certain input features, and when searching for feature assignments altering the prediction. Furthermore, we present a novel and hierarchical definition of verified explanations, termed verifier-optimal robust explanations, that explicitly factors the incompleteness of network verifiers within the explanation. Our comprehensive experimental evaluation demonstrates the superior scalability of both FaVeX, and of verifier-optimal robust explanations, which together can produce meaningful formal explanation on networks with hundreds of thousands of non-linear activations.
Cite as

Alessandro De Palma, Greta Dolcetti, and Caterina Urban. Faster Verified Explanations for Neural Networks. In 40th European Conference on Object-Oriented Programming (ECOOP 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 372, pp. 3:1-3:32, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{depalma_et_al:LIPIcs.ECOOP.2026.3,
  author =	{De Palma, Alessandro and Dolcetti, Greta and Urban, Caterina},
  title =	{{Faster Verified Explanations for Neural Networks}},
  booktitle =	{40th European Conference on Object-Oriented Programming (ECOOP 2026)},
  pages =	{3:1--3:32},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-423-9},
  ISSN =	{1868-8969},
  year =	{2026},
  volume =	{372},
  editor =	{Krebbers, Robbert and Silva, Alexandra},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECOOP.2026.3},
  URN =		{urn:nbn:de:0030-drops-260999},
  doi =		{10.4230/LIPIcs.ECOOP.2026.3},
  annote =	{Keywords: Verified Explanations, eXplainable Artificial Intelligence (XAI), Local Robustness, Neural Network Verification, Static Analysis}
}
Document
DOI: 10.4230/DagRep.15.10.37
Sound Static Program Analysis in Modern Software Engineering (Dagstuhl Seminar 25421)

Authors: Pietro Ferrara, Liana Hadarean, Jorge A. Navas, Caterina Urban, and Greta Dolcetti

Published in: Dagstuhl Reports, Volume 15, Issue 10 (2026)

Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 25421 "Sound Static Program Analysis in Modern Software Engineering". Sound Static Program Analysis (SSPA) has historically been effective in proving the absence of runtime errors and security vulnerabilities, notably in safety-critical embedded software. However, it has seen limited adoption in desktop applications until its revival for Web application security (e.g., to prove the absence of SQL injection vulnerabilities). Modern software development, characterized by architectures like microservices, serverless computing, and the increasing use of scripting languages, presents challenges to SSPA due to the integration of multiple languages and complex semantics, while also posing new problems related to soundness, precision, and scalability stemming from the machine learning revolution in code development. Despite these new opportunities for SSPA to offer structured feedback and address serious flaws often overlooked by the shallow analyses currently favored by the industry, there has not been a significant resurgence in its industrial application. This Dagstuhl Seminar aimed to bridge the SSPA and software engineering communities to extend existing theories to these new trends, foster integration with modern practices like DevOps, and discuss the formal methods challenges arising from contemporary software architectures.
Cite as

Pietro Ferrara, Liana Hadarean, Jorge A. Navas, Caterina Urban, and Greta Dolcetti. Sound Static Program Analysis in Modern Software Engineering (Dagstuhl Seminar 25421). In Dagstuhl Reports, Volume 15, Issue 10, pp. 37-74, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@Article{ferrara_et_al:DagRep.15.10.37,
  author =	{Ferrara, Pietro and Hadarean, Liana and Navas, Jorge A. and Urban, Caterina and Dolcetti, Greta},
  title =	{{Sound Static Program Analysis in Modern Software Engineering (Dagstuhl Seminar 25421)}},
  pages =	{37--74},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2026},
  volume =	{15},
  number =	{10},
  editor =	{Ferrara, Pietro and Hadarean, Liana and Navas, Jorge A. and Urban, Caterina and Dolcetti, Greta},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.15.10.37},
  URN =		{urn:nbn:de:0030-drops-254154},
  doi =		{10.4230/DagRep.15.10.37},
  annote =	{Keywords: Abstract interpretation, Formal methods, Software engineering, Software verification, Sound static program analysis}
}
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact