通信学报2026，Vol.47Issue(5)：103-112,10.DOI:10.11959/j.issn.1000-436x.TXXB260119
融合多尺度语义与VMD-BiLSTM的恶意APP检测模型
Malicious APP detection model integrating multi-scale semantics and VMD-BiLSTM
摘要
Abstract
To address the challenges of difficult feature extraction,high background noise,and a lack of model transpar-ency in identifying malicious applications within encrypted traffic,a novel detection model integrating variational mode decomposition(VMD),Attention-BiLSTM,and the SHAP mechanism was proposed.Firstly,targeting the multi-scale characteristics of mobile APP traffic,an adaptive multi-scale window mechanism was designed to dynamically extract and construct semantic-driven high-dimensional time series.Secondly,to mitigate the complex environmental noise inter-twined within these structured sequences,VMD was introduced for frequency-domain stationary denoising.Subse-quently,an Attention-BiLSTM network coupled with focal loss was employed to accurately capture long-range temporal dependencies.Finally,the SHAP mechanism was incorporated to quantify the marginal contributions of features,provid-ing post-hoc attribution explanations to facilitate decision traceability.Experimental results demonstrate that the pro-posed model achieves an accuracy of 0.981 8,successfully realizing high-precision detection while simultaneously en-hancing the transparency and credibility of the model's decision-making process.关键词
恶意APP识别/自适应多尺度窗口/流量异常检测/变分模态分解/双向长短期记忆网络/可解释性分析Key words
malicious APP identification/adaptive multi-scale window/traffic anomaly detection/VMD/BiLSTM/inter-pretability analysis分类
信息技术与安全科学引用本文复制引用
许国良,时磊,邱思琦,许宇..融合多尺度语义与VMD-BiLSTM的恶意APP检测模型[J].通信学报,2026,47(5):103-112,10.基金项目
国家自然科学基金资助项目(No.U23A20275) The National Natural Science Foundation of China(No.U23A20275) （No.U23A20275）
