用机器学习检测假网址、垃圾邮件和网络日志，提升浏览器安全
Browser Extension for Fake URL Detection
- 集成三种功能的浏览器插件，用ML识别钓鱼网站
- 钓鱼网站识别准确率96.5%，垃圾邮件识别精度达100%
- 适合关注在线安全的普通用户和开发者使用
近年来，网络攻击数量激增，攻击强度与对用户的潜在危害也显著上升。在技术快速发展的背景下，用户难以跟上最新动态，容易遭受攻击。为此，需借助工具防范风险，而机器学习模型是理想选择。本文提出一款浏览器扩展，集成三项核心功能：恶意网址检测、垃圾邮件识别与网络日志分析。用于钓鱼网站分类的LGBM模型基于包含87个特征的数据集训练，达到96.5%的准确率、96.8%的精确率和96.49%的F1分数。垃圾邮件检测模型采用多项式朴素贝叶斯（Multinomial NB），在超过5500条消息的数据集上训练，实现97.09%的准确率和100%的精确率。结果表明，机器学习在网络安全领域具有显著有效性。
原文摘要 · Abstract (English)
In recent years, Cyber attacks have increased in number, and with them, the intensity of the attacks and their potential to damage the user have also increased significantly. In an ever-advancing world, users find it difficult to keep up with the latest developments in technology, which can leave them vulnerable to attacks. To avoid such situations we need tools to deter such attacks, for this machine learning models are among the best options. This paper presents a Browser Extension that uses machine learning models to enhance online security by integrating three crucial functionalities: Malicious URL detection, Spam Email detection and Network logs analysis. The proposed solution uses LGBM classifier for classification of Phishing websites, the model has been trained on a dataset with 87 features, this model achieved an accuracy of 96.5% with a precision of 96.8% and F1 score of 96.49%. The Model for Spam email detection uses Multinomial NB algorithm which has been trained on a dataset with over 5500 messages, this model achieved an accuracy of 97.09% with a precision of 100%. The results demonstrate the effectiveness of using machine learning models for cyber security.
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。