LAMeD: LLM-generated Annotations for Memory Leak Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shemetova, Ekaterina, Shenbin, Ilya, Smirnov, Ivan, Alekseev, Anton, Rukhovich, Alexey, Nikolenko, Sergey, Lomshakov, Vadim, Piontkovskaya, Irina
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916719724855296
author Shemetova, Ekaterina
Shenbin, Ilya
Smirnov, Ivan
Alekseev, Anton
Rukhovich, Alexey
Nikolenko, Sergey
Lomshakov, Vadim
Piontkovskaya, Irina
author_facet Shemetova, Ekaterina
Shenbin, Ilya
Smirnov, Ivan
Alekseev, Anton
Rukhovich, Alexey
Nikolenko, Sergey
Lomshakov, Vadim
Piontkovskaya, Irina
contents Static analysis tools are widely used to detect software bugs and vulnerabilities but often struggle with scalability and efficiency in complex codebases. Traditional approaches rely on manually crafted annotations -- labeling functions as sources or sinks -- to track data flows, e.g., ensuring that allocated memory is eventually freed, and code analysis tools such as CodeQL, Infer, or Cooddy can use function specifications, but manual annotation is laborious and error-prone, especially for large or third-party libraries. We present LAMeD (LLM-generated Annotations for Memory leak Detection), a novel approach that leverages large language models (LLMs) to automatically generate function-specific annotations. When integrated with analyzers such as Cooddy, LAMeD significantly improves memory leak detection and reduces path explosion. We also suggest directions for extending LAMeD to broader code analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02376
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LAMeD: LLM-generated Annotations for Memory Leak Detection
Shemetova, Ekaterina
Shenbin, Ilya
Smirnov, Ivan
Alekseev, Anton
Rukhovich, Alexey
Nikolenko, Sergey
Lomshakov, Vadim
Piontkovskaya, Irina
Software Engineering
Static analysis tools are widely used to detect software bugs and vulnerabilities but often struggle with scalability and efficiency in complex codebases. Traditional approaches rely on manually crafted annotations -- labeling functions as sources or sinks -- to track data flows, e.g., ensuring that allocated memory is eventually freed, and code analysis tools such as CodeQL, Infer, or Cooddy can use function specifications, but manual annotation is laborious and error-prone, especially for large or third-party libraries. We present LAMeD (LLM-generated Annotations for Memory leak Detection), a novel approach that leverages large language models (LLMs) to automatically generate function-specific annotations. When integrated with analyzers such as Cooddy, LAMeD significantly improves memory leak detection and reduces path explosion. We also suggest directions for extending LAMeD to broader code analysis.
title LAMeD: LLM-generated Annotations for Memory Leak Detection
topic Software Engineering
url https://arxiv.org/abs/2505.02376