基于图神经网络和多特征融合的有害网站检测研究OA

To address the limitations of current harmful website detection methods in deep text semantic mining and multimodal feature co-perception,this study proposes a multi-feature fusion detection model based on graph attention networks(GAT)and ConvNeXt.The framework leverages GloVe word embeddings to construct semantic representations of website text,mapping it into a graph structure based on word co-occurrence relationships.The adaptive attention mechanism in GAT dynamically captures contextual dependencies between non-contiguous words,while ConvNeXt extracts both local details and global contextual features from website images.A cross-attention-based fusion module facilitates dynamic text-image feature alignment and interactive integration.Experimental results demonstrate that the proposed model achieves 99.10％accuracy in four-category website classification,significantly enhancing detection performance.This work offers valuable insights for identifying harmful online content and enhancing cybersecurity governance.