Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Wenbo, Song, Shiwen, Guo, Jiaxun, Xu, Zhengzi, Liu, Chengwei, Ou, Haoran, Ge, Mengmeng, Liu, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917219387047936
author Guo, Wenbo
Song, Shiwen
Guo, Jiaxun
Xu, Zhengzi
Liu, Chengwei
Ou, Haoran
Ge, Mengmeng
Liu, Yang
author_facet Guo, Wenbo
Song, Shiwen
Guo, Jiaxun
Xu, Zhengzi
Liu, Chengwei
Ou, Haoran
Ge, Mengmeng
Liu, Yang
contents Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks, yet existing detection methods either depend on fragile handcrafted rules or data-driven features that fail to capture evolving attack semantics. We present IntelGuard, a retrieval-augmented generation (RAG) based framework that integrates expert analytical reasoning into automated malicious package detection. IntelGuard constructs a structured knowledge base from over 8,000 threat intelligence reports, linking malicious code snippets with behavioral descriptions and expert reasoning. When analyzing new packages, it retrieves semantically similar malicious examples and applies LLM-guided reasoning to assess whether code behaviors align with intended functionality. Experiments on 4,027 real-world packages show that IntelGuard achieves 99% accuracy and a 0.50% false positive rate, while maintaining 96.5% accuracy on obfuscated code. Deployed on PyPI.org, it discovered 54 previously unreported malicious packages, demonstrating interpretable and robust detection guided by expert knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16458
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages
Guo, Wenbo
Song, Shiwen
Guo, Jiaxun
Xu, Zhengzi
Liu, Chengwei
Ou, Haoran
Ge, Mengmeng
Liu, Yang
Software Engineering
Cryptography and Security
Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks, yet existing detection methods either depend on fragile handcrafted rules or data-driven features that fail to capture evolving attack semantics. We present IntelGuard, a retrieval-augmented generation (RAG) based framework that integrates expert analytical reasoning into automated malicious package detection. IntelGuard constructs a structured knowledge base from over 8,000 threat intelligence reports, linking malicious code snippets with behavioral descriptions and expert reasoning. When analyzing new packages, it retrieves semantically similar malicious examples and applies LLM-guided reasoning to assess whether code behaviors align with intended functionality. Experiments on 4,027 real-world packages show that IntelGuard achieves 99% accuracy and a 0.50% false positive rate, while maintaining 96.5% accuracy on obfuscated code. Deployed on PyPI.org, it discovered 54 previously unreported malicious packages, demonstrating interpretable and robust detection guided by expert knowledge.
title Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages
topic Software Engineering
Cryptography and Security
url https://arxiv.org/abs/2601.16458