Назад к обновлениям
UpdatedAug 31, 2026

Awesome-LLMs-for-Vulnerability-Detection — Updated!

Сообщество, наиболее полный и постоянно обновляемый индекс исследований по большим языковым моделям для обнаружения уязвимостей в программном обеспечении — статьи по обнаружению на уровне функций, репозиториев, агентному и смарт-контрактному обнаружению, а также наборы данных, бенчмарки и обзоры.

Поделиться

Awesome Large Language Models for Vulnerability Detection

Кураторский список статей, проектов и навыков агентов по использованию LLM для обнаружения и выявления уязвимостей.


📄 Статьи

Показаны только работы 2025 года и новее. Для более ранних работ см. Архив статей (2024 и ранее).

НазваниеПлощадкаГодСтатьяGithub
VulnGym: Benchmarking Coding Agents for Repository-Level Vulnerability Detection2026ссылкассылка
VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection2026ссылкассылка
Synthesizing Multi-Agent Harnesses for Vulnerability Discovery2026ссылкассылка
QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Vulnerability Discovery2026ссылка
Seclens: Role-specific Evaluation of LLM's for security vulnerablity detection2026ссылкассылка
Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap2026ссылка
Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive FilteringISSTA2026ссылка
AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection2026ссылка
LLM-based Vulnerability Detection at Project Scale: An Empirical Study2026ссылка
MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution2026ссылка
VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security SpecificationsFSE2026ссылкассылка
VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection2025ссылка
VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization2025ссылка
From Large to Mammoth: A Comparative Evaluation of Large Language Models in Vulnerability DetectionNDSS2025ссылка
Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code RepositoriesACL2025ссылкассылка
A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models2025ссылкассылка
LLMxCPG: Context-Aware Vulnerability Detection Through Code Property Graph-Guided Large Language ModelsUsenix2025ссылкассылка
CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code RepresentationACL Findings2025ссылкассылка
Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond2025ссылкассылка
Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models2025ссылка
SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability AnalysisSP2025ссылкассылка
SecVulEval: Benchmarking LLMs for Real-World C/C++ Vulnerability Detection2025linklink
CVE-Bench: Benchmarking LLM-based Software Engineering Agent's Ability to Repair Real-World CVE VulnerabilitiesNAACL2025linklink
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation2025linklink
Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns2025link
Context-Enhanced Vulnerability Detection Based on Large Language Model2025link
Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask2025linklink
MOS: Towards Effective Smart Contract Vulnerability Detection through Mixture-of-Experts Tuning of Large Language Models2025link
Abundant Modalities Offer More Nutrients: Multi-Modal-Based Function-Level Vulnerability DetectionTOSEM2025linklink
Generative Large Language Model usage in Smart Contract Vulnerability Detection2025link
Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDEICSE2025linklink
Vulnerability Detection with Code Language Models: How Far Are We?ICSE2025linklink
Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with JustificationsICSE2025link
LAMD: Context-driven Android Malware Detection and Classification with LLMs2025link
LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights2025linklink
One-for-All Does Not Work! Enhancing Vulnerability Detection by Mixture-of-Experts (MoE)2025link

🚀 Проекты

Категории