Reproduce “MalRAG: A Retrieval-Augmented LLM Framework for Open-set Malicious Traffic Identification” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiang Luo, Chang Liu, Gang Xiong, Chen Yang, Gaopeng Gou, Yaochen Ren, Zhen Li
MalRAG identifies known malicious traffic classes and flags flows that do not match its labeled database as novel. It retrieves examples across payload, packet-length, and timing views to guide a frozen large language model, without fine-tuning. On USTC-2016, it reports macro-F1 0.9928 and normalized accuracy from 0.72 to 0.85 across three tested chronological scenarios; it does not name new attack families.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.