Die umfassendste, kontinuierlich aktualisierte Sammlung der Community zu Forschung über Large Language Models zur Erkennung von Software-Schwachstellen – mit Papers zu Funktionsebene, Repository-Ebene, agentischer und Smart-Contract-Erkennung sowie Datensätzen, Benchmarks und Übersichtsarbeiten.
# Awesome Large Language Models for Vulnerability Detection Eine kuratierte Liste von Papers, Projekten und Agent Skills zur Nutzung von LLMs für die Erkennung und Entdeckung von Schwachstellen. --- ## 📄 Papers > Es werden nur Arbeiten ab 2025 angezeigt. Für frühere Arbeiten siehe [Papers Archive (2024 and earlier)](https://github.com/huhusmang/awesome-llms-for-vulnerability-detection/blob/main/docs/papers_archive.md). | Titel | Veranstaltung | Jahr | Paper | Github | | :---: | :---: | :--: | :---: | :---: | | VulnGym: Benchmarking Coding Agents for Repository-Level Vulnerability Detection | | 2026 | [link](https://arxiv.org/abs/2608.02001) | [link](https://github.com/Tencent/VulnGym) | | VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection | | 2026 | [link](https://arxiv.org/abs/2605.09461) | [link](https://github.com/vinsontang1/VulTriage) | | Synthesizing Multi-Agent Harnesses for Vulnerability Discovery | | 2026 | [link](https://arxiv.org/abs/2604.20801) | [link](https://github.com/berabuddies/agentflow) | | QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Vulnerability Discovery | | 2026 | [link](https://arxiv.org/abs/2602.09774) | | | Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection | | 2026 | [link](https://arxiv.org/abs/2604.01637) | [link](https://github.com/mattersec-labs/seclens) | | Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap | | 2026 | [link](https://arxiv.org/abs/2601.22655) | | | Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering | ISSTA | 2026 | [link](https://arxiv.org/abs/2601.22952) | | | AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection | | 2026 | [link](https://arxiv.org/abs/2601.19138) | | | LLM-based Vulnerability Detection at Project Scale: An Empirical Study | | 2026 | [link](https://arxiv.org/abs/2601.19239) | | | MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution | | 2026 | [link](https://arxiv.org/abs/2601.18847) | | | VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications | FSE | 2026 | [link](https://arxiv.org/abs/2511.04014) | [link](https://github.com/zhuhaopku/VulInstruct) | | VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection | | 2025 | [link](https://arxiv.org/abs/2512.07533) | | | VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization | | 2025 | [link](https://arxiv.org/abs/2511.11896) | | | From Large to Mammoth: A Comparative Evaluation of Large Language Models in Vulnerability Detection | NDSS | 2025 | [link](https://www.ndss-symposium.org/ndss-paper/from-large-to-mammoth-a-comparative-evaluation-of-large-language-models-in-vulnerability-detection/) | | | Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories | ACL | 2025 | [link](https://aclanthology.org/2025.acl-long.1490/) | [link](https://github.com/alperen21/JitVul) | | A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models | | 2025 | [link](https://arxiv.org/abs/2507.22659) | [link](https://github.com/hs-esslingen-it-security/Awesome-LLM4SVD) | | LLMxCPG: Context-Aware Vulnerability Detection Through Code Property Graph-Guided Large Language Models | Usenix | 2025 | [link](https://arxiv.org/abs/2507.16585) | [link](https://github.com/qcri/llmxcpg) | | CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation | ACL Findings | 2025 | [link](https://aclanthology.org/2025.findings-acl.414/) | [link](https://github.com/yoimiya-nlp/CLeVeR) | | Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond | | 2025 | [link](https://arxiv.org/abs/2506.03651) | [link](https://github.com/vul337/mono) | | Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models | | 2025 | [link](https://arxiv.org/abs/2505.17460) | | | SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis | SP | 2025 | [link](https://arxiv.org/abs/2505.20630) | [link](https://github.com/Jackline97/SV-TrustEval-C) | | SecVulEval: Benchmarking LLMs for Real-World C/C++ Vulnerability Detection | | 2025 | [link](https://arxiv.org/abs/2505.19828) | [link](https://github.com/basimbd/secvuleval) | | CVE-Bench: Benchmarking LLM-based Software Engineering Agent's Ability to Repair Real-World CVE Vulnerabilities | NAACL | 2025 | [link](https://aclanthology.org/2025.naacl-long.212/) | [link](https://github.com/WhileBug/CVEBench) | | R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation | | 2025 | [link](https://arxiv.org/abs/2504.04699) | [link](https://github.com/martin-wey/R2Vul) | | Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns | | 2025 | [link](https://arxiv.org/abs/2504.16057) | | | Context-Enhanced Vulnerability Detection Based on Large Language Model | | 2025 | [link](https://arxiv.org/abs/2504.16877) | | | Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask | | 2025 | [link](https://arxiv.org/abs/2504.13474) | [link](https://anonymous.4open.science/r/CORRECT/README.md) | | MOS: Towards Effective Smart Contract Vulnerability Detection through Mixture-of-Experts Tuning of Large Language Models | | 2025 | [link](https://arxiv.org/abs/2504.12234) | | | Abundant Modalities Offer More Nutrients: Multi-Modal-Based Function-Level Vulnerability Detection | TOSEM | 2025 | [link](https://dl.acm.org/doi/10.1145/3731557) | [link](https://github.com/vinci-grape/MVulD) | | Generative Large Language Model usage in Smart Contract Vulnerability Detection | | 2025 | [link](https://arxiv.org/abs/2504.04685) | | | Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDE | ICSE | 2025 | [link](https://www.arxiv.org/abs/2412.14306) | [link](https://doi.org/10.6084/m9.figshare.26367139) | | Vulnerability Detection with Code Language Models: How Far Are We? | ICSE | 2025 | [link](https://arxiv.org/abs/2403.18624) | [link](https://github.com/DLVulDet/PrimeVul) | | Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications | ICSE | 2025 | [link](https://arxiv.org/abs/2403.16073) | | | LAMD: Context-driven Android Malware Detection and Classification with LLMs | | 2025 | [link](http://arxiv.org/abs/2502.13055) | | | LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights | | 2025 | [link](https://arxiv.org/abs/2502.07049) | [link](https://github.com/OwenSanzas/LLM-For-Software-Security) | | One-for-All Does Not Work! Enhancing Vulnerability Detection by Mixture-of-Experts (MoE) | | 2025 | [link](https://arxiv.org/abs/2501.16454) | | --- ## 🚀 Projekte | Name | Beschreibung | Github | | :---: | :---: | :---: | | OpenAnt (Knostic) | LLM-gestützte mehrstufige Schwachstellenerkennung mit adversarialer Verifikation | [link](https://github.com/knostic/OpenAnt) | | DeepAudit | Multi-Agenten-KI-Red-Team-Plattform mit Exploit-Validierung in Docker-Sandbox | [link](https://github.com/lintsinghua/DeepAudit) | | AutoCVE | Automatisierte Schwachstellenerkennung und -meldung mit Multi-Agenten-Architektur | [link](https://github.com/larlarua/AutoCVE) | | Darkmoon | Open-Source-Plattform (GPL-3.0) für autonome KI-Pentests und MCP-Host; technologiespezifische offensive Sub-Agenten, Abdeckung von Active Directory und Kubernetes, über 80 orchestrierte Tools, Nachweiskette pro Fund | [link](https://github.com/ASCIT31/Dark-Moon) | | strix | Open-Source-Tool für autonome KI-Penetrationstests via pip | [link](https://github.com/usestrix/strix) | | deepsec (Vercel) | Sicherheits-Harness für tiefgehende Schwachstellen-Scans von Codebasen mit Coding-Agenten | [link](https://github.com/vercel-labs/deepsec) | | rust-in-peace | Agentengestützte Schwachstellenerkennung für Rust mit adversarialer Triage, dynamischer Verifikation und einem experimentellen Profil zur Analyse von Android-APKs | [link](https://github.com/scadastrangelove/rust-in-peace) | --- ## 🧩 Agent Skills | Name | Beschreibung | Link | | :---: | :---: | :---: | | codex-security (OpenAI) | Autonomes Schwachstellen-Scanning auf Repository-Ebene via Codex-Agenten | [link](https://openai.com/index/codex-security-now-in-research-preview/) | | defending-code-reference-harness (Anthropic) | Referenz-Skills für Threat Modeling, Scanning, Triage und Patchen mit Claude Code | [link](https://github.com/anthropics/defending-code-reference-harness) | | security-audit-skill (Cloudflare) | Sechsphasige Security-Audit-Skill mit parallelen Hunting-Agenten und adversarialer Validierung | [link](https://github.com/cloudflare/security-audit-skill) | --- ## 📡 arxiv.md Automatisierte tägliche Erfassung und Aktualisierung von Arxiv-Papers für festgelegte Schlüsselwörter über Workflows. ## Danksagungen Der Workflow „Updated Arxiv Papers Daily“ des Projekts orientiert sich an diesem Projekt [LLM4SE](https://github.com/gai4se/LLM4SE). Ich habe dessen ursprünglichen Code überarbeitet, indem ich die Bibliothek [arxiv](https://github.com/lukasschwab/arxiv.py) verwendet habe.