Repairing Regex Vulnerabilities via Localization-Guided Instructions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sung, Sicheol, Hahn, Joonghyuk, Han, Yo-Sub
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914085899075584
author Sung, Sicheol
Hahn, Joonghyuk
Han, Yo-Sub
author_facet Sung, Sicheol
Hahn, Joonghyuk
Han, Yo-Sub
contents Regular expressions (regexes) are foundational to modern computing for critical tasks like input validation and data parsing, yet their ubiquity exposes systems to regular expression denial of service (ReDoS), a vulnerability requiring automated repair methods. Current approaches, however, are hampered by a trade-off. Symbolic, rule-based system are precise but fails to repair unseen or complex vulnerability patterns. Conversely, large language models (LLMs) possess the necessary generalizability but are unreliable for tasks demanding strict syntactic and semantic correctness. We resolve this impasse by introducing a hybrid framework, localized regex repair (LRR), designed to harness LLM generalization while enforcing reliability. Our core insight is to decouple problem identification from the repair process. First, a deterministic, symbolic module localizes the precise vulnerable subpattern, creating a constrained and tractable problem space. Then, the LLM invoked to generate a semantically equivalent fix for this isolated segment. This combined architecture successfully resolves complex repair cases intractable for rule-based repair while avoiding the semantic errors of LLM-only approaches. Our work provides a validated methodology for solving such problems in automated repair, improving the repair rate by 15.4%p over the state-of-the-art. Our code is available at https://github.com/cdltlehf/LRR.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Repairing Regex Vulnerabilities via Localization-Guided Instructions
Sung, Sicheol
Hahn, Joonghyuk
Han, Yo-Sub
Artificial Intelligence
Programming Languages
68T50
I.2.7
Regular expressions (regexes) are foundational to modern computing for critical tasks like input validation and data parsing, yet their ubiquity exposes systems to regular expression denial of service (ReDoS), a vulnerability requiring automated repair methods. Current approaches, however, are hampered by a trade-off. Symbolic, rule-based system are precise but fails to repair unseen or complex vulnerability patterns. Conversely, large language models (LLMs) possess the necessary generalizability but are unreliable for tasks demanding strict syntactic and semantic correctness. We resolve this impasse by introducing a hybrid framework, localized regex repair (LRR), designed to harness LLM generalization while enforcing reliability. Our core insight is to decouple problem identification from the repair process. First, a deterministic, symbolic module localizes the precise vulnerable subpattern, creating a constrained and tractable problem space. Then, the LLM invoked to generate a semantically equivalent fix for this isolated segment. This combined architecture successfully resolves complex repair cases intractable for rule-based repair while avoiding the semantic errors of LLM-only approaches. Our work provides a validated methodology for solving such problems in automated repair, improving the repair rate by 15.4%p over the state-of-the-art. Our code is available at https://github.com/cdltlehf/LRR.
title Repairing Regex Vulnerabilities via Localization-Guided Instructions
topic Artificial Intelligence
Programming Languages
68T50
I.2.7
url https://arxiv.org/abs/2510.09037