2 Search Results for "Moscato, Mariano M."

Document
DOI: 10.4230/LIPIcs.SAT.2025.32
Efficient Certified Reasoning for Binarized Neural Networks

Authors: Jiong Yang, Yong Kiam Tan, Mate Soos, Magnus O. Myreen, and Kuldeep S. Meel

Published in: LIPIcs, Volume 341, 28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025)

Abstract
Neural networks have emerged as essential components in safety-critical applications - these use cases demand complex, yet trustworthy computations. Binarized Neural Networks (BNNs) are a type of neural network where each neuron is constrained to a Boolean value; they are particularly well-suited for safety-critical tasks because they retain much of the computational capacities of full-scale (floating-point or quantized) deep neural networks, but remain compatible with satisfiability solvers for qualitative verification and with model counters for quantitative reasoning. However, existing methods for BNN analysis suffer from either limited scalability or susceptibility to soundness errors, which hinders their applicability in real-world scenarios. In this work, we present a scalable and trustworthy approach for both qualitative and quantitative verification of BNNs. Our approach introduces a native representation of BNN constraints in a custom-designed solver for qualitative reasoning, and in an approximate model counter for quantitative reasoning. We further develop specialized proof generation and checking pipelines with native support for BNN constraint reasoning, ensuring trustworthiness for all of our verification results. Empirical evaluations on a BNN robustness verification benchmark suite demonstrate that our certified solving approach achieves a 9× speedup over prior certified CNF and PB-based approaches, and our certified counting approach achieves a 218× speedup over the existing CNF-based baseline. In terms of coverage, our pipeline produces fully certified results for 99% and 86% of the qualitative and quantitative reasoning queries on BNNs, respectively. This is in sharp contrast to the best existing baselines which can fully certify only 62% and 4% of the queries, respectively.
Cite as

Jiong Yang, Yong Kiam Tan, Mate Soos, Magnus O. Myreen, and Kuldeep S. Meel. Efficient Certified Reasoning for Binarized Neural Networks. In 28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 341, pp. 32:1-32:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{yang_et_al:LIPIcs.SAT.2025.32,
  author =	{Yang, Jiong and Tan, Yong Kiam and Soos, Mate and Myreen, Magnus O. and Meel, Kuldeep S.},
  title =	{{Efficient Certified Reasoning for Binarized Neural Networks}},
  booktitle =	{28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025)},
  pages =	{32:1--32:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-381-2},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{341},
  editor =	{Berg, Jeremias and Nordstr\"{o}m, Jakob},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.SAT.2025.32},
  URN =		{urn:nbn:de:0030-drops-237665},
  doi =		{10.4230/LIPIcs.SAT.2025.32},
  annote =	{Keywords: Neural network verification, proof certification, SAT solving, approximate model counting}
}
Document
DOI: 10.4230/LIPIcs.ITP.2021.27
Formal Verification of Termination Criteria for First-Order Recursive Functions

Authors: Cesar A. Muñoz, Mauricio Ayala-Rincón, Mariano M. Moscato, Aaron M. Dutle, Anthony J. Narkawicz, Ariane A. Almeida, Andréia B. Avelar, and Thiago M. Ferreira Ramos

Published in: LIPIcs, Volume 193, 12th International Conference on Interactive Theorem Proving (ITP 2021)

Abstract
This paper presents a formalization of several termination criteria for first-order recursive functions. The formalization, which is developed in the Prototype Verification System (PVS), includes the specification and proof of equivalence of semantic termination, Turing termination, size change principle, calling context graphs, and matrix-weighted graphs. These termination criteria are defined on a computational model that consists of a basic functional language called PVS0, which is an embedding of recursive first-order functions. Through this embedding, the native mechanism for checking termination of recursive functions in PVS could be soundly extended with semi-automatic termination criteria such as calling contexts graphs.
Cite as

Cesar A. Muñoz, Mauricio Ayala-Rincón, Mariano M. Moscato, Aaron M. Dutle, Anthony J. Narkawicz, Ariane A. Almeida, Andréia B. Avelar, and Thiago M. Ferreira Ramos. Formal Verification of Termination Criteria for First-Order Recursive Functions. In 12th International Conference on Interactive Theorem Proving (ITP 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 193, pp. 27:1-27:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)

Copy BibTex To Clipboard

@InProceedings{munoz_et_al:LIPIcs.ITP.2021.27,
  author =	{Mu\~{n}oz, Cesar A. and Ayala-Rinc\'{o}n, Mauricio and Moscato, Mariano M. and Dutle, Aaron M. and Narkawicz, Anthony J. and Almeida, Ariane A. and Avelar, Andr\'{e}ia B. and M. Ferreira Ramos, Thiago},
  title =	{{Formal Verification of Termination Criteria for First-Order Recursive Functions}},
  booktitle =	{12th International Conference on Interactive Theorem Proving (ITP 2021)},
  pages =	{27:1--27:17},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-188-7},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{193},
  editor =	{Cohen, Liron and Kaliszyk, Cezary},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITP.2021.27},
  URN =		{urn:nbn:de:0030-drops-139228},
  doi =		{10.4230/LIPIcs.ITP.2021.27},
  annote =	{Keywords: Formal Verification, Termination, Calling Context Graph, PVS}
}
  • Refine by Type
  • 2 Document/PDF
  • 1 Document/HTML

  • Refine by Publication Year
  • 1 2025
  • 1 2021

  • Refine by Author
  • 1 Almeida, Ariane A.
  • 1 Avelar, Andréia B.
  • 1 Ayala-Rincón, Mauricio
  • 1 Dutle, Aaron M.
  • 1 M. Ferreira Ramos, Thiago
  • Show More...

  • Refine by Series/Journal
  • 2 LIPIcs

  • Refine by Classification
  • 1 Computing methodologies → Artificial intelligence
  • 1 Computing methodologies → Neural networks
  • 1 Computing methodologies → Theorem proving algorithms
  • 1 Software and its engineering → Software verification
  • 1 Theory of computation → Logic and verification
  • Show More...

  • Refine by Keyword
  • 1 Calling Context Graph
  • 1 Formal Verification
  • 1 Neural network verification
  • 1 PVS
  • 1 SAT solving
  • Show More...

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