DROPS

Document

DOI: 10.4230/LIPIcs.AFT.2024.7

DeFiAligner: Leveraging Symbolic Analysis and Large Language Models for Inconsistency Detection in Decentralized Finance

Authors: Rundong Gan, Liyi Zhou, Le Wang, Kaihua Qin, and Xiaodong Lin

Published in: LIPIcs, Volume 316, 6th Conference on Advances in Financial Technologies (AFT 2024)

Abstract

Decentralized Finance (DeFi) has witnessed a monumental surge, reaching 53.039 billion USD in total value locked. As this sector continues to expand, ensuring the reliability of DeFi smart contracts becomes increasingly crucial. While some users are adept at reading code or the compiled bytecode to understand smart contracts, many rely on documentation. Therefore, discrepancies between the documentation and the deployed code can pose significant risks, whether these discrepancies are due to errors or intentional fraud. To tackle these challenges, we developed DeFiAligner, an end-to-end system to identify inconsistencies between documentation and smart contracts. DeFiAligner incorporates a symbolic execution tool, SEVM, which explores execution paths of on-chain binary code, recording memory and stack states. It automatically generates symbolic expressions for token balance changes and branch conditions, which, along with related project documents, are processed by LLMs. Using structured prompts, the LLMs evaluate the alignment between the symbolic expressions and the documentation. Our tests across three distinct scenarios demonstrate DeFiAligner’s capability to automate inconsistency detection in DeFi, achieving recall rates of 92% and 90% on two public datasets respectively.

Cite as

Rundong Gan, Liyi Zhou, Le Wang, Kaihua Qin, and Xiaodong Lin. DeFiAligner: Leveraging Symbolic Analysis and Large Language Models for Inconsistency Detection in Decentralized Finance. In 6th Conference on Advances in Financial Technologies (AFT 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 316, pp. 7:1-7:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{gan_et_al:LIPIcs.AFT.2024.7,
  author =	{Gan, Rundong and Zhou, Liyi and Wang, Le and Qin, Kaihua and Lin, Xiaodong},
  title =	{{DeFiAligner: Leveraging Symbolic Analysis and Large Language Models for Inconsistency Detection in Decentralized Finance}},
  booktitle =	{6th Conference on Advances in Financial Technologies (AFT 2024)},
  pages =	{7:1--7:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-345-4},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{316},
  editor =	{B\"{o}hme, Rainer and Kiffer, Lucianna},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.AFT.2024.7},
  URN =		{urn:nbn:de:0030-drops-209431},
  doi =		{10.4230/LIPIcs.AFT.2024.7},
  annote =	{Keywords: Decentralized Finance Security, Large Language Models, Project Review, Symbolic Analysis, Smart Contracts}
}

Document

DOI: 10.4230/LIPIcs.ECOOP.2020.15

Static Analysis of Shape in TensorFlow Programs

Authors: Sifis Lagouvardos, Julian Dolby, Neville Grech, Anastasios Antoniadis, and Yannis Smaragdakis

Published in: LIPIcs, Volume 166, 34th European Conference on Object-Oriented Programming (ECOOP 2020)

Abstract

Machine learning has been widely adopted in diverse science and engineering domains, aided by reusable libraries and quick development patterns. The TensorFlow library is probably the best-known representative of this trend and most users employ the Python API to its powerful back-end. TensorFlow programs are susceptible to several systematic errors, especially in the dynamic typing setting of Python. We present Pythia, a static analysis that tracks the shapes of tensors across Python library calls and warns of several possible mismatches. The key technical aspects are a close modeling of library semantics with respect to tensor shape, and an identification of violations and error-prone patterns. Pythia is powerful enough to statically detect (with 84.62% precision) 11 of the 14 shape-related TensorFlow bugs in the recent Zhang et al. empirical study - an independent slice of real-world bugs.

Cite as

Sifis Lagouvardos, Julian Dolby, Neville Grech, Anastasios Antoniadis, and Yannis Smaragdakis. Static Analysis of Shape in TensorFlow Programs. In 34th European Conference on Object-Oriented Programming (ECOOP 2020). Leibniz International Proceedings in Informatics (LIPIcs), Volume 166, pp. 15:1-15:29, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@InProceedings{lagouvardos_et_al:LIPIcs.ECOOP.2020.15,
  author =	{Lagouvardos, Sifis and Dolby, Julian and Grech, Neville and Antoniadis, Anastasios and Smaragdakis, Yannis},
  title =	{{Static Analysis of Shape in TensorFlow Programs}},
  booktitle =	{34th European Conference on Object-Oriented Programming (ECOOP 2020)},
  pages =	{15:1--15:29},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-154-2},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{166},
  editor =	{Hirschfeld, Robert and Pape, Tobias},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECOOP.2020.15},
  URN =		{urn:nbn:de:0030-drops-131726},
  doi =		{10.4230/LIPIcs.ECOOP.2020.15},
  annote =	{Keywords: Python, TensorFlow, static analysis, Doop, Wala}
}

Document

Artifact

DOI: 10.4230/DARTS.6.2.6

Static Analysis of Shape in TensorFlow Programs (Artifact)

Authors: Sifis Lagouvardos, Julian Dolby, Neville Grech, Anastasios Antoniadis, and Yannis Smaragdakis

Published in: DARTS, Volume 6, Issue 2, Special Issue of the 34th European Conference on Object-Oriented Programming (ECOOP 2020)

Abstract

These instructions are intended for using the artifact for our ECOOP'20 paper entitled "Static Analysis of Shape in TensorFlow Programs". They can be used to run Pythia - the tool implementing the paper’s analysis - on the paper’s evaluation set demonstrating bug detection in the most precise configuration of our analysis as well as the precision of the analysis under different configurations.

Cite as

Sifis Lagouvardos, Julian Dolby, Neville Grech, Anastasios Antoniadis, and Yannis Smaragdakis. Static Analysis of Shape in TensorFlow Programs (Artifact). In Special Issue of the 34th European Conference on Object-Oriented Programming (ECOOP 2020). Dagstuhl Artifacts Series (DARTS), Volume 6, Issue 2, pp. 6:1-6:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@Article{lagouvardos_et_al:DARTS.6.2.6,
  author =	{Lagouvardos, Sifis and Dolby, Julian and Grech, Neville and Antoniadis, Anastasios and Smaragdakis, Yannis},
  title =	{{Static Analysis of Shape in TensorFlow Programs (Artifact)}},
  pages =	{6:1--6:3},
  journal =	{Dagstuhl Artifacts Series},
  ISSN =	{2509-8195},
  year =	{2020},
  volume =	{6},
  number =	{2},
  editor =	{Lagouvardos, Sifis and Dolby, Julian and Grech, Neville and Antoniadis, Anastasios and Smaragdakis, Yannis},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DARTS.6.2.6},
  URN =		{urn:nbn:de:0030-drops-132035},
  doi =		{10.4230/DARTS.6.2.6},
  annote =	{Keywords: Python, TensorFlow, static analysis, Doop, Wala}
}

3 Search Results for "Lagouvardos, Sifis"

DeFiAligner: Leveraging Symbolic Analysis and Large Language Models for Inconsistency Detection in Decentralized Finance

Abstract

Cite as

Static Analysis of Shape in TensorFlow Programs

Abstract

Cite as

Static Analysis of Shape in TensorFlow Programs (Artifact)

Abstract

Cite as

Thanks for your feedback!

Could not send message