Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jan 9, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

994

使用深度学习和大型语言模型轻量级恶意URL检测.

Hareem Kibriya1, Rashid Amin2, Sultan S Alshamrani3

  • 1Department of Computer Science, Air University, Islamabad, Pakistan.

Scientific reports
|December 2, 2025
PubMed
概括
此摘要是机器生成的。

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Federated ConvNeXt-swin temporal fusion network for malware and botnet detection in IoT systems.

Scientific reports·2026
Same author

Improving IoT security through an explainable hybrid CNN-transformer model and federated learning.

Scientific reports·2026
Same author

FC-FTCP: a lightweight fault-tolerant clustering protocol for secure IoT data transmission.

Scientific reports·2026
Same author

In vitro and in vivo investigations of antibacterial B-TCP/polymer composite enhanced with strontium for bone grafting and photocatalytic applications.

Cytotechnology·2026
Same author

Exploring the lived experience of physical and mental illness using a hermeneutic phenomenological framework.

Journal of health psychology·2026
Same author

Enhancement of cryptography algorithms for security of cloud-based IoT with machine learning models.

Scientific reports·2026
Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026
Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026
Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026
Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026
Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026
Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026
查看所有相关文章

本研究引入了使用大型语言模型检测恶意URL的深度学习框架,达到97.5%的准确性. 该系统以提高透明度高效地对网络鱼和恶意软件等威胁进行分类.

科学领域:

  • 网络安全 网络安全
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 恶意网站的扩散带来了重大的网络安全风险,包括数据泄露和身份盗窃.
  • 现有的机器学习 (ML) 检测恶意URL的方法通常依赖于手动功能工程,并与不断变化的威胁作斗争.
  • 需要自动化,适应性的解决方案来有效地识别和减轻在线威胁.

研究的目的:

  • 开发一个完全自动化的深度学习 (DL) 框架,用于检测恶意统一资源定位器 (URL).
  • 利用大型语言模型 (LLM) 在没有手动功能工程的情况下生成URL嵌入式.
  • 以高的准确性和效率将URL分类为恶意 (变形,恶意软件,网络鱼) 和良性类别.

主要方法:

  • 利用大型语言模型 (LLM) 来创建高质量的URL嵌入,捕捉复杂的模式和代码关系.
  • 采用了定制的深度学习模型,结合了长短期记忆 (LSTM) 和门式循环单元 (GRU) 层进行依赖性分析.
  • 整合了来自变压器的双向编码器表示 (BERT) 与DL模型,并使用了可解释AI (XAI) 技术,如本地可解释模型-不可知解释 (LIME) 以提高透明度.

主要成果:

  • 使用BERT + DL模型检测恶意URL的最高准确率为97.5%.

更多相关视频

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K

相关实验视频

Last Updated: Jan 9, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

994
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.4K
  • 伯特+DL模型表现出高效率,仅用50万个参数在0.119毫秒内对样品进行分类.
  • 局部可解释的模型不可知解释 (LIME) 为模型的决策过程提供了透明度.

    • 结论:

    • 拟议的深度学习框架有效地检测出恶意URL,并且具有最先进的准确性和效率.
    • 使用LLMs和BERT显著减少了手动特征工程的需求,提高了适应性.
    • 集成XAI提高了网络安全实时应用的模型可信度和可靠性.