DROPS

Document

DOI: 10.4230/LIPIcs.SAT.2025.4

Bit-Precise Reasoning with Parametric Bit-Vectors

Authors: Zvika Berger, Yoni Zohar, Aina Niemetz, Mathias Preiner, Andrew Reynolds, Clark Barrett, and Cesare Tinelli

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

Abstract

The SMT-LIB theory of bit-vectors is restricted to bit-vectors of fixed width. However, several important applications can benefit from reasoning about bit-vectors of symbolic widths, i.e., parametric bit-vectors. Recent work has introduced an approach for solving formulas over parametric bit-vectors, via an eager translation to quantified integer arithmetic with uninterpreted functions. The approach was shown to be successful for several applications, including the bit-width independent verification of compiler optimizations, invertibility conditions, and rewrite rules. We extend and improve that approach in several aspects. Theoretically, we improve expressiveness by defining a new theory of parametric bit-vectors that supports more operators and allows reasoning about the bit-widths themselves. Algorithmically, we introduce a lazy algorithm that avoids the use of uninterpreted functions and quantified axioms for them. Empirically, we show a significant improvement by implementing and evaluating our approach, and comparing it experimentally to the previous one.

Cite as

Zvika Berger, Yoni Zohar, Aina Niemetz, Mathias Preiner, Andrew Reynolds, Clark Barrett, and Cesare Tinelli. Bit-Precise Reasoning with Parametric Bit-Vectors. In 28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 341, pp. 4:1-4:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{berger_et_al:LIPIcs.SAT.2025.4,
  author =	{Berger, Zvika and Zohar, Yoni and Niemetz, Aina and Preiner, Mathias and Reynolds, Andrew and Barrett, Clark and Tinelli, Cesare},
  title =	{{Bit-Precise Reasoning with Parametric Bit-Vectors}},
  booktitle =	{28th International Conference on Theory and Applications of Satisfiability Testing (SAT 2025)},
  pages =	{4:1--4:24},
  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.2025.4},
  URN =		{urn:nbn:de:0030-drops-237385},
  doi =		{10.4230/LIPIcs.SAT.2025.4},
  annote =	{Keywords: Satisfiability Modulo Theories, Bit-precise Reasoning, Parametric Bit-vectors}
}

Document

DOI: 10.4230/LIPIcs.CONCUR.2023.26

DNN Verification, Reachability, and the Exponential Function Problem

Authors: Omri Isac, Yoni Zohar, Clark Barrett, and Guy Katz

Published in: LIPIcs, Volume 279, 34th International Conference on Concurrency Theory (CONCUR 2023)

Abstract

Deep neural networks (DNNs) are increasingly being deployed to perform safety-critical tasks. The opacity of DNNs, which prevents humans from reasoning about them, presents new safety and security challenges. To address these challenges, the verification community has begun developing techniques for rigorously analyzing DNNs, with numerous verification algorithms proposed in recent years. While a significant amount of work has gone into developing these verification algorithms, little work has been devoted to rigorously studying the computability and complexity of the underlying theoretical problems. Here, we seek to contribute to the bridging of this gap. We focus on two kinds of DNNs: those that employ piecewise-linear activation functions (e.g., ReLU), and those that employ piecewise-smooth activation functions (e.g., Sigmoids). We prove the two following theorems: (i) the decidability of verifying DNNs with a particular set of piecewise-smooth activation functions, including Sigmoid and tanh, is equivalent to a well-known, open problem formulated by Tarski; and (ii) the DNN verification problem for any quantifier-free linear arithmetic specification can be reduced to the DNN reachability problem, whose approximation is NP-complete. These results answer two fundamental questions about the computability and complexity of DNN verification, and the ways it is affected by the network’s activation functions and error tolerance; and could help guide future efforts in developing DNN verification tools.

Cite as

Omri Isac, Yoni Zohar, Clark Barrett, and Guy Katz. DNN Verification, Reachability, and the Exponential Function Problem. In 34th International Conference on Concurrency Theory (CONCUR 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 279, pp. 26:1-26:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{isac_et_al:LIPIcs.CONCUR.2023.26,
  author =	{Isac, Omri and Zohar, Yoni and Barrett, Clark and Katz, Guy},
  title =	{{DNN Verification, Reachability, and the Exponential Function Problem}},
  booktitle =	{34th International Conference on Concurrency Theory (CONCUR 2023)},
  pages =	{26:1--26:18},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-299-0},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{279},
  editor =	{P\'{e}rez, Guillermo A. and Raskin, Jean-Fran\c{c}ois},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CONCUR.2023.26},
  URN =		{urn:nbn:de:0030-drops-190205},
  doi =		{10.4230/LIPIcs.CONCUR.2023.26},
  annote =	{Keywords: Formal Verification, Computability Theory, Deep Neural Networks}
}

Search Results

Documents authored by Zohar, Yoni

Bit-Precise Reasoning with Parametric Bit-Vectors

Abstract

Cite as

DNN Verification, Reachability, and the Exponential Function Problem

Abstract

Cite as

Thanks for your feedback!

Could not send message