DROPS

Artifact

Software

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}
}

Search Results

Documents authored by De Palma, Alessandro

FaVeX

Abstract

Cite as

Faster Verified Explanations for Neural Networks

Abstract

Cite as

Thanks for your feedback!

Could not send message