Bridging Code Property Graphs and Language Models for Program Analysis

• URL: http://arxiv.org/abs/2603.24837v1
• Date: Wed, 25 Mar 2026 22:08:04 GMT
• Title: Bridging Code Property Graphs and Language Models for Program Analysis
• Abstract summary: Large Language Models (LLMs) face critical challenges when analyzing security vulnerabilities in real worlds.<n> token limits prevent loading entire repositories, code embeddings fail to capture inter procedural data flows, and LLMs struggle to generate complex static analysis queries.<n>We introduce codebadger, an open source Model Context Protocol (MCP) server that integrates Joern's Code Property Graph engine with LLMs.
• Score: 1.7158296436650338
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) face critical challenges when analyzing security vulnerabilities in real world codebases: token limits prevent loading entire repositories, code embeddings fail to capture inter procedural data flows, and LLMs struggle to generate complex static analysis queries. These limitations force existing approaches to operate on isolated code snippets, missing vulnerabilities that span multiple functions and files. We introduce codebadger, an open source Model Context Protocol (MCP) server that integrates Joern's Code Property Graph (CPG) engine with LLMs. Rather than requiring LLMs to generate complex CPG queries, codebadger provides high level tools for program slicing, taint tracking, data flow analysis, and semantic code navigation, enabling targeted exploration of large codebases without exhaustive file reading. We demonstrate its effectiveness through three use cases: (1) navigating an 8,000 method codebase to audit memory safety patterns, (2) discovering and exploiting a previously unreported buffer overflow in libtiff, and (3) generating a correct patch for an integer overflow vulnerability (CVE-2025-6021) in libxml2 on the first attempt. codebadger enables LLMs to reason about code semantically across entire repositories, supporting vulnerability discovery, patching, and program comprehension at scale.

Related papers

• LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories [0.0]
  Large language models (LLMs) are increasingly used to generate and assist with software development.<n>Existing vulnerability datasets largely focus on human-written code or controlled environments.<n>We present LLMVul, a vulnerability-labeled dataset of LLM-generated C/C++ functions mined from real production repositories.
  arXiv  Detail & Related papers  (2026-09-10T01:10:12Z)
• Functional and Secure Code Generation with Task Vectors [7.757776817999749]
  Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities.<n>We develop a novel method, SecVecCoder, leveraging task vectors to produce trustworthy code that is simultaneously functional and secure.
  arXiv  Detail & Related papers  (2026-07-08T19:32:22Z)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• Multi-Agent Taint Specification Extraction for Vulnerability Detection [49.27772068704498]
  Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results.<n>We present SemTaint, a multi-agent system that strategically combines the semantic understanding of Large Language Models (LLMs) with traditional static program analysis.<n>We integrate SemTaint with CodeQL, a state-of-the-art SAST tool, and demonstrate its effectiveness by detecting 106 of 162 vulnerabilities previously undetectable by CodeQL.
  arXiv  Detail & Related papers  (2026-01-15T21:31:51Z)
• Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback [1.1017250479834206]
  Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors.<n>We propose a retrieval-augmented, multi-tool repair workflow in which a single code-generating LLM iteratively refines its outputs.
  arXiv  Detail & Related papers  (2026-01-01T23:34:00Z)
• LLM-GUARD: Large Language Model-Based Detection and Repair of Bugs and Security Vulnerabilities in C++ and Python [0.0]
  Large Language Models (LLMs) such as ChatGPT-4, Claude 3, and LLaMA 4 are increasingly embedded in software/application development.<n>This study presents a systematic, empirical evaluation of these three leading LLMs using a benchmark of programming errors, classic security flaws, and advanced, production-grade bugs in C++ and Python.
  arXiv  Detail & Related papers  (2025-08-22T14:30:24Z)
• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Decompiling Smart Contracts with a Large Language Model [51.49197239479266]
  Despite Etherscan's 78,047,845 smart contracts deployed on (as of May 26, 2025), a mere 767,520 ( 1%) are open source.<n>This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode.<n>We introduce a pioneering decompilation pipeline that transforms bytecode into human-readable and semantically faithful Solidity code.
  arXiv  Detail & Related papers  (2025-06-24T13:42:59Z)
• CodeRAG: Supportive Code Retrieval on Bigraph for Real-World Code Generation [69.684886175768]
  Large language models (LLMs) have shown promising performance in automated code generation.<n>In this paper, we propose CodeRAG, a retrieval-augmented code generation framework.<n> Experiments show that CodeRAG achieves significant improvements compared to no RAG scenarios.
  arXiv  Detail & Related papers  (2025-04-14T09:51:23Z)
• HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data [60.75578581719921]
  Large language models (LLMs) have shown great potential for automatic code generation. Recent studies highlight that many LLM-generated code contains serious security vulnerabilities. We introduce HexaCoder, a novel approach to enhance the ability of LLMs to generate secure codes.
  arXiv  Detail & Related papers  (2024-09-10T12:01:43Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• Can LLMs Patch Security Issues? [1.3299507495084417]
  Large Language Models (LLMs) have shown impressive proficiency in code generation. LLMs share a weakness with their human counterparts: producing code that inadvertently has security vulnerabilities. We propose Feedback-Driven Security Patching (FDSP), where LLMs automatically refine generated, vulnerable code.
  arXiv  Detail & Related papers  (2023-11-13T08:54:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.