发表机构
University of Electronic Science and Technology of China; City University of Hong Kong; Key Laboratory of Intelligent Digital Media Technology of Sichuan Province（电子科技大学; 香港城市大学; 四川省智能数字媒体技术重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究网络流量异常检测，针对曼巴多视图扫描存在冗余积累问题，提出DisenMamba框架，将多视图扫描改为解缠再融合过程，有效防止不变信息积累，保留多视图线索，经实验验证其有效性并建立新范式。
AI 中文摘要
网络流量异常检测（NTAD）是网络安全中的一项关键任务，但及时准确的异常检测仍具有挑战性。曼巴因其对长序列建模的线性时间复杂度，成为NTAD特别有前景的主干。它还采用专用多视图扫描机制通过互补上下文线索提高检测精度。然而，我们发现多视图曼巴扫描存在先前被忽视的结构缺陷：冗余积累。具体而言，不同扫描分支捕获大量视图不变信息，在多视图融合时反复放大，而视图特定信息被稀释甚至抑制，导致表示同质化和多视图退化。为解决此问题，我们提出DisenMamba，一种新颖的解缠多视图曼巴框架。DisenMamba将多视图扫描重新制定为两阶段解缠然后融合的过程，在融合前明确分离视图不变和视图特定组件。此设计防止不变信息积累，同时保留互补多视图线索，为细微流量异常产生更具判别力的表示。广泛实验证明了DisenMamba的有效性，建立了新的解缠多视图曼巴范式。代码可在该https URL获取。
英文摘要
Network Traffic Anomaly Detection (NTAD) is a critical task in cybersecurity, yet timely and accurate anomaly detection remains challenging. Mamba has emerged as a particularly promising backbone for NTAD due to its linear-time complexity for long-sequence modeling. It further incorporates a dedicated multi-view scanning mechanism to enhance detection precision through complementary contextual cues. However, we identify a previously overlooked structural deficiency in multi-view Mamba scanning for NTAD: redundancy accumulation. Specifically, distinct scanning branches capture substantial view-invariant information, which is repeatedly amplified during multi-view fusion; conversely, view-specific information is diluted or even suppressed, leading to representation homogenization and multi-view degradation. To address this problem, we propose DisenMamba, a novel disentangled multi-view Mamba framework. DisenMamba reformulates multi-view scanning as a two-stage disentangle-then-fuse process that explicitly separates view-invariant and view-specific components prior to fusion. This design prevents the invariant information accumulation while preserving complementary multi-view cues, yielding more discriminative representations for subtle traffic anomalies. Extensive experiments demonstrate the effectiveness of DisenMamba, establishing a new disentangled multi-view Mamba paradigm. Code is available at https://github.com/ikun0124/DisenMamba.
CommentsAccepted by KDD 2026
