Awesome-LLMs-for-Vulnerability-Detection - The community's most comprehensive, continuously-u

项目说明

Awesome Large Language Models for Detection

A curated list of papers, projects, and agent skills on using LLMs for detection and discovery.

---

📄 Papers

> Only showing 2025 and later. For earlier work, see Papers Archive (2024 and earlier).

| Title | Venue | Year | Paper | Github |
| :---: | :---: | :--: | :---: | :---: |
| : Benchmarking Coding Agents for Repository-Le Detection | | 2026 | link | link |
| : Triple-Path Context Augmentation for LLM-Based Detection | | 2026 | link | link |
| Synthesizing Multi-Agent Harnesses for Discovery | | 2026 | link | link |
| QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Discovery | | 2026 | link | |
| Seclens: Role-specific E of LLM's for security detection | | 2026 | link | link |
| Do Fine-Tuned LLMs Understand ? An In into the Semantic Trap | | 2026 | link | |
| Sifting the Noise: A Comparati of LLM Agents in False Positi | ISSTA | 2026 | link | |
| AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Detection | | 2026 | link | |
| LLM-based Detection at Project Scale: An Empirical Study | | 2026 | link | |
| MulVul: Retrie Multi-Agent Code Detection Prompt E | | 2026 | link | |
| : Specialized Reasoning LLM with Agent Scaffold for Detection | | 2025 | link | |
| VULPO: Context-Aware Detection LLM Optimization | | 2025 | link | |
| : Teaching LLMs Root-Cause Reasoning for Detection Specifications | | 2025 | link | |
| From Large to Mammoth: A Comparati of Large Language Models in Detection | NDSS | 2025 | link | |
| Benchmarking LLMs and LLM-based Agents in Practical Detection for Code Repositories | ACL | 2025 | link | link |
| A Systematic Literature Review on Detecting Software with Large Language Models | | 2025 | link | link |
| LLMxCPG: Context-Aware Detection Through Code Property Graph-Guided Large Language Models | Usenix | 2025 | link | link |
| CLeVeR: Multi-modal Contrasti for Code Representation | ACL Findings | 2025 | link | link |
| Mono: Is Your "Clean" Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond | | 2025 | link | link |
| Learning to Focus: Context Extraction for Efficient Code Detection with Language Models | | 2025 | link | |
| S: E Structure and Semantic Reasoning in Large Language Models for Source Code Analysis | SP | 2025 | link | link |
| Sec: Benchmarking LLMs for Real-World C/C++ Detection | | 2025 | link | link |
| C: Benchmarking LLM-based Software Engineering Agent's Ability to Repair Real-World C | NAACL | 2025 | link | link |
| R2Vul: Learning to Reason about Software with Reinforcement Learning and Structured Reasoning Distillation | | 2025 | link | link |
| Neuro-symbolic Static Analysis with LLM-generated Patterns | | 2025 | link | |
| Context-Enhanced Detection Based on Large Language Model | | 2025 | link | |
| E You Wanted to Know About LLM-based Detection But Were Afraid to Ask | | 2025 | link | link |
| MOS: Towards Effecti Contract Detection through Mixture-of-Experts Tuning of Large Language Models | | 2025 | link | |
| Abundant Modalities Offer More Nutrients: Multi-Modal-Based Function-Le Detection | TOSEM | 2025 | link | link |
| Generati Language Model usage in Smart Contract Detection | | 2025 | link | |
| Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Detection & Repair in the IDE | ICSE | 2025 | link | link |
| Detection with Code Language Models: How Far Are We? | ICSE | 2025 | link | link |
| Combining Fine-Tuning and LLM-based Agents for Intuiti Contract Auditing with Justifications | ICSE | 2025 | link | |
| LAMD: Context-dri Malware Detection and Classification with LLMs | | 2025 | link | |
| LLMs in Software Security: A Survey of Detection Techniques and Insights | | 2025 | link | link |
| One-for-All Does Not Work! Enhancing Detection by Mixture-of-Experts (MoE) | | 2025 | link | |

---

🚀 Projects

| Name | Description | Github |
| :---: | :---: | :---: |
| OpenAnt (Knostic) | LLM-powered multi-stage discovery with ad | link |
| DeepAudit | Multi-agent AI red-team platform with Docker sandbox exploit | link |
| AutoCVE | Automated detection and reporting with multi-agent architecture | link |
| Darkmoon | Open-source (GPL-3.0) autonomous AI pentest platform and MCP host; per-technology offensi, Acti and Kubernetes co, 80+ orchestrated tools, e trail per finding | link |
| strix | Open-source autonomous AI penetration testing tool via pip | link |
| deepsec () | Security harness for deep codebase scanning with coding agents | link |

---

🧩 Agent Skills

| Name | Description | Link |
| :---: | :---: | :---: |
| codex-security (OpenAI) | Autonomous repo-le scanning agents | link |
| defending-code-reference-harness (Anthropic) | Reference skills for threat modeling, scanning, triage, and patching with Claude Code | link |
| security-audit-skill (Cloudflare) | Six-phase security audit skill with parallel hunting agents and ad | link |

---

📡 arxiv.md

Automated daily capture and update of Arxi for specified keywords through workflows.

Acknowledgements

The project's Updated Arxi Daily workflow borrows from this project LLM4SE. I refactored its original code by using the arxiv library.

项目信息

开发语言：Python

Star 数：1428

技术要点

该项目属于漏洞知识库方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。