# IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities

arXiv: https://arxiv.org/abs/2405.17238 · HTML: https://mlsanity.com/paper/2405.17238/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2024.

## Built on by (most cited first, 30 of 103)

- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing](https://mlsanity.com/paper/2501.18160/) (2025)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [BaxBench: Can LLMs Generate Correct and Secure Backends?](https://mlsanity.com/paper/2502.11844/) (2025)
- [Repo2Run: Automated Building Executable Environment for Code Repository at Scale](https://mlsanity.com/paper/2502.13681/) (2025)
- [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025)
- [KNighter: Transforming Static Analysis with LLM-Synthesized Checkers](https://mlsanity.com/paper/2503.09002/) (2025)
- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [A Survey on Agentic Security: Applications, Threats and Defenses](https://mlsanity.com/paper/2510.06445/) (2025)
- [Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study](https://mlsanity.com/paper/2506.08311/) (2025)
- [Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering](https://mlsanity.com/paper/2504.07137/) (2025)
- [SECURE: Benchmarking Large Language Models for Cybersecurity](https://mlsanity.com/paper/2405.20441/) (2024)
- [FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents](https://mlsanity.com/paper/2507.15241/) (2025)
- [A Contemporary Survey of Large Language Model Assisted Program Analysis](https://mlsanity.com/paper/2502.18474/) (2025)
- [VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection](https://mlsanity.com/paper/2512.07533/) (2025)
- [From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security](https://mlsanity.com/paper/2412.15004/) (2024)
- [CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection](https://mlsanity.com/paper/2503.09433/) (2025)
- [Rethinking the Evaluation of Secure Code Generation](https://mlsanity.com/paper/2503.15554/) (2025)
- [Locus: Agentic Predicate Synthesis for Directed Fuzzing](https://mlsanity.com/paper/2508.21302/) (2025)
- [LProtector: An LLM-driven Vulnerability Detection System](https://mlsanity.com/paper/2411.06493/) (2024)
- [OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification](https://mlsanity.com/paper/2504.20964/) (2025)
- [Enhancing Automated Loop Invariant Generation for Complex Programs with Large Language Models](https://mlsanity.com/paper/2412.10483/) (2024)
- [Reasoning with LLMs for Zero-Shot Vulnerability Detection](https://mlsanity.com/paper/2503.17885/) (2025)
- [RFCAudit: An LLM Agent for Functional Bug Detection in Network Protocols](https://mlsanity.com/paper/2506.00714/) (2025)
- [AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models](https://mlsanity.com/paper/2506.14682/) (2025)
- [A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks](https://mlsanity.com/paper/2511.00872/) (2025)
- [When Agents Do Not Stop: Uncovering Infinite Agentic Loops in LLM Agents](https://mlsanity.com/paper/2607.01641/) (2026)
- [Harnessing the Power of LLMs in Source Code Vulnerability Detection](https://mlsanity.com/paper/2408.03489/) (2024)

## Abstract (arXiv)

Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code generation capabilities but they cannot do complex reasoning over code to detect such vulnerabilities especially since this task requires whole-repository analysis. We propose IRIS, a neuro-symbolic approach that systematically combines LLMs with static analysis to perform whole-repository reasoning for security vulnerability detection. Specifically, IRIS leverages LLMs to infer taint specifications and perform contextual analysis, alleviating needs for human specifications and inspection. For evaluation, we curate a new dataset, CWE-Bench-Java, comprising 120 manually validated security vulnerabilities in real-world Java projects. A state-of-the-art static analysis tool CodeQL detects only 27 of these vulnerabilities whereas IRIS with GPT-4 detects 55 (+28) and improves upon CodeQL's average false discovery rate by 5% points. Furthermore, IRIS identifies 4 previously unknown vulnerabilities which cannot be found by existing tools. IRIS is available publicly at https://github.com/iris-sast/iris.