用混合模型实时识别恶意网址，准确率超96%
A Hybrid Deep Learning and Anomaly Detection Framework for Real-Time Malicious URL Classification
- 融合哈希向量化、SMOTE平衡与孤立森林过滤的多阶段处理流程
- 达96.4%准确率、20毫秒预测延迟，速度比CNN快50至100倍
- 支持多语言界面和剪贴板实时检测，适合安全监控场景
恶意网址仍是网络钓鱼、恶意软件及网络威胁的主要途径。本文提出一种混合深度学习框架，结合哈希向量化n-gram分析、SMOTE数据平衡、孤立森林异常过滤与轻量级神经网络分类器，实现对开源仓库中网址的实时分类。该多阶段流程提取长度、点号数量、熵值等统计特征，训练复杂度为O(NL + EBdh)，预测延迟仅为20毫秒。实验表明，该方法准确率达96.4%，F1得分为95.4%，ROC-AUC为97.3%，优于CNN（94.8%）和SVM基线，且提速50至100倍（见表~\ref{tab:comp-complexity}）。系统配备多语言Tkinter图形界面（阿拉伯语/英语/法语），支持剪贴板集成，可实时评估威胁。框架展现出优异的可扩展性与对抗混淆网址模式的鲁棒性。
原文摘要 · Abstract (English)
Malicious URLs remain a primary vector for phishing, malware, and cyberthreats. This study proposes a hybrid deep learning framework combining \texttt{HashingVectorizer} n-gram analysis, SMOTE balancing, Isolation Forest anomaly filtering, and a lightweight neural network classifier for real-time URL classification. The multi-stage pipeline processes URLs from open-source repositories with statistical features (length, dot count, entropy), achieving $O(NL + EBdh)$ training complexity and a 20\,ms prediction latency. Empirical evaluation yields 96.4\% accuracy, 95.4\% F1-score, and 97.3\% ROC-AUC, outperforming CNN (94.8\%) and SVM baselines with a $50\!\times$--$100\!\times$ speedup (Table~\ref{tab:comp-complexity}). A multilingual Tkinter GUI (Arabic/English/French) enables real-time threat assessment with clipboard integration. The framework demonstrates superior scalability and resilience against obfuscated URL patterns.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。