A Literature Review on Verification and Abstraction of Neural
Networks Within the Formal Methods Community

C 2025

A Literature Review on Verification and Abstraction of Neural Networks Within the Formal Methods Community

KANAV, Sudeep; Jan KŘETÍNSKÝ a Sabine RIEDER

Základní údaje

Originální název

A Literature Review on Verification and Abstraction of Neural Networks Within the Formal Methods Community

Autoři

KANAV, Sudeep; Jan KŘETÍNSKÝ a Sabine RIEDER

Vydání

Cham, Switzerland, Principles of Verification: Cycling the Probabilistic Landscape : Essays Dedicated to Joost-Pieter Katoen on the Occasion of His 60th Birthday, od s. 39-65, 27 s. Lecture Notes in Computer Science, 15262, 2025

Nakladatel

Springer

Další údaje

Jazyk

angličtina

Typ výsledku

Kapitola resp. kapitoly v odborné knize

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Označené pro přenos do RIV

Ano

Organizační jednotka

Fakulta informatiky

ISBN

978-3-031-75777-8

DOI

https://doi.org/10.1007/978-3-031-75778-5_3

EID Scopus

2-s2.0-85212145354

Klíčová slova anglicky

Neural Networks; Neural Networks Verification; Neural Networks Abstraction

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 1. 4. 2026 10:45, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

With the increasing interest in applying neural networks (NNs) to safety-critical problems like autonomous driving or unmanned aircrafts, ensuring the reliability of these NNs becomes essential. Therefore, several verification techniques have been proposed in recent years. Additionally, various abstraction techniques have been developed to enable verification of larger NNs. As the area develops, different surveys on verification of NNs are being published. However, we are missing a systematic summarization of knowledge through the lens of formal methods. In this literature review, we provide a systematic overview of techniques for verification and abstraction of NNs published in well-known formal verification conferences during the last ten years.

Návaznosti

MUNI/A/1081/2022, interní kód MU

Název: Modelování, analýza a verifikace (2023)

Investor: Masarykova univerzita, Modelování, analýza a verifikace (2023)

MUNI/A/1433/2022, interní kód MU

Název: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity 23

Investor: Masarykova univerzita, Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity 23

MUNI/I/1757/2021, interní kód MU

Název: MUNI Award in Science and Humanities (Akronym: Křetínský)

Investor: Masarykova univerzita, MUNI Award in Science and Humanities, MASH - MUNI Award in Science and Humanities

Citovat

KANAV, Sudeep; Jan KŘETÍNSKÝ a Sabine RIEDER. A Literature Review on Verification and Abstraction of Neural Networks Within the Formal Methods Community. In Principles of Verification: Cycling the Probabilistic Landscape : Essays Dedicated to Joost-Pieter Katoen on the Occasion of His 60th Birthday. Cham, Switzerland: Springer, 2025, s. 39-65. Lecture Notes in Computer Science, 15262. ISBN 978-3-031-75777-8. Dostupné z: https://doi.org/10.1007/978-3-031-75778-5_3.

@inbook{2469721,
   author = {Kanav, Sudeep and Křetínský, Jan and Rieder, Sabine},
   address = {Cham, Switzerland},
   booktitle = {Principles of Verification: Cycling the Probabilistic Landscape : Essays Dedicated to Joost-Pieter Katoen on the Occasion of His 60th Birthday},
   doi = {https://doi.org/10.1007/978-3-031-75778-5_3},
   keywords = {Neural Networks; Neural Networks Verification; Neural Networks Abstraction},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham, Switzerland},
   isbn = {978-3-031-75777-8},
   pages = {39-65},
   publisher = {Springer},
   title = {A Literature Review on Verification and Abstraction of Neural Networks Within the Formal Methods Community},
   year = {2025}
}

TY  - CHAP
ID  - 2469721
AU  - Kanav, Sudeep - Křetínský, Jan - Rieder, Sabine
PY  - 2025
TI  - A Literature Review on Verification and Abstraction of Neural Networks Within the Formal Methods Community
VL  - Lecture Notes in Computer Science, 15262
PB  - Springer
CY  - Cham, Switzerland
SN  - 9783031757778
KW  - Neural Networks
KW  - Neural Networks Verification
KW  - Neural Networks Abstraction
N2  - With the increasing interest in applying neural networks (NNs) to safety-critical problems like autonomous driving or unmanned aircrafts, ensuring the reliability of these NNs becomes essential. Therefore, several verification techniques have been proposed in recent years. Additionally, various abstraction techniques have been developed to enable verification of larger NNs. As the area develops, different surveys on verification of NNs are being published. However, we are missing a systematic summarization of knowledge through the lens of formal methods. In this literature review, we provide a systematic overview of techniques for verification and abstraction of NNs published in well-known formal verification conferences during the last ten years.
ER  -

KANAV, Sudeep; Jan KŘETÍNSKÝ a Sabine RIEDER. A Literature Review on Verification and Abstraction of Neural Networks Within the Formal Methods Community. In \textit{Principles of Verification: Cycling the Probabilistic Landscape : Essays Dedicated to Joost-Pieter Katoen on the Occasion of His 60th Birthday}. Cham, Switzerland: Springer, 2025, s.~39-65. Lecture Notes in Computer Science, 15262. ISBN~978-3-031-75777-8. Dostupné z: https://doi.org/10.1007/978-3-031-75778-5\_{}3.

Přehled o publikaci