MAGE-ID：一种多模态生成框架用于入侵检测系统
MAGE-ID: A Multimodal Generative Framework for Intrusion Detection Systems
AI总结：
MAGE-ID通过多模态生成框架提升入侵检测系统的数据增强效果，实现更平衡和一致的多模态合成，显著提升检测性能。
摘要：
现代入侵检测系统（IDS）面临严重挑战，原因包括异构网络流量、不断演变的网络威胁以及良性与攻击流量之间的数据不平衡。尽管生成模型在数据增强方面显示出潜力，但现有方法局限于单一模态，无法捕捉跨域依赖关系。本文介绍了MAGE-ID（多模态攻击生成器用于入侵检测），一种基于扩散的生成框架，通过统一的潜在先验将表格流量特征与其转换后的图像耦合在一起。通过联合训练基于Transformer和CNN的变分编码器，并使用EDM风格的去噪器，MAGE-ID实现了平衡且一致的多模态合成。在CIC-IDS-2017和NSL-KDD上的评估显示，MAGE-ID在保真度、多样性以及下游检测性能方面均优于TabSyn和TabDDPM，凸显了MAGE-ID在多模态IDS增强方面的有效性。
英文摘要：
Modern Intrusion Detection Systems (IDS) face severe challenges due to heterogeneous network traffic, evolving cyber threats, and pronounced data imbalance between benign and attack flows. While generative models have shown promise in data augmentation, existing approaches are limited to single modalities and fail to capture cross-domain dependencies. This paper introduces MAGE-ID (Multimodal Attack Generator for Intrusion Detection), a diffusion-based generative framework that couples tabular flow features with their transformed images through a unified latent prior. By jointly training Transformer and CNN-based variational encoders with an EDM style denoiser, MAGE-ID achieves balanced and coherent multimodal synthesis. Evaluations on CIC-IDS-2017 and NSL-KDD demonstrate significant improvements in fidelity, diversity, and downstream detection performance over TabSyn and TabDDPM, highlighting the effectiveness of MAGE-ID for multimodal IDS augmentation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
