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

相关概念视频

Types of Errors: Detection and Minimization01:12

Types of Errors: Detection and Minimization

Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...

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

Medical application driven content based medical image retrieval system for enhanced analysis of X-ray images.

Scientific reports·2025
Same author

Designing green robots with environmental sustainability by applying the concept of multi-criteria decision making.

Scientific reports·2025
Same author

Dynamic load balancing in cloud computing using predictive graph networks and adaptive neural scheduling.

Scientific reports·2025
Same author

ESHA-256_GBGO: a high-performance and optimized security framework for internet of medical thing.

Scientific reports·2025
Same author

Capsule network approach for monkeypox (CAPSMON) detection and subclassification in medical imaging system.

Scientific reports·2025
Same author

Hybrid quantum enhanced federated learning for cyber attack detection.

Scientific reports·2024

相关实验视频

Updated: Jun 28, 2026

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

683

微薄的注意力与剩余的金字塔深度可分离的卷积式基于恶意软件的检测与优化机制.

B Ranjani1, M Chinnadurai2

  • 1Department of Computer Science and Engineering, E.G.S. Pillay Engineering College, Nagapattinam, Tamil Nadu, 611002, India. ranjanimecse1315@gmail.com.

Scientific reports
|October 17, 2024
PubMed
概括
此摘要是机器生成的。

这项研究引入了一种用于云恶意软件检测的新型深度学习方法,将API调用转换为图像,以提高识别威胁的准确性和效率.

关键词:
不同类型的波器过器注意力机制注意力机制深度学习是一种深度学习.密集的网络 密集的网络恶意软件是一种恶意软件.剩余单位单位 剩余单位单位白优化白的优化

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

478
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

1.4K

相关实验视频

Last Updated: Jun 28, 2026

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

683
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

478
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

1.4K

科学领域:

  • 网络安全 网络安全
  • 机器学习 机器学习
  • 云计算 云计算 云计算 云计算

背景情况:

  • 恶意软件对云系统的安全性和隐私构成重大风险.
  • 传统的基于签名的恶意软件检测方法对不断变化的威胁无效.
  • 现有的API调用分析模型面临准确性和分类挑战.

研究的目的:

  • 为云环境开发基于深度学习的高级恶意软件检测系统.
  • 通过使用基于图像的API调用分析来解决现有方法的局限性.
  • 为了提高恶意软件分类的准确性和效率.

主要方法:

  • 将API调用数据转换为2D灰度图像进行分析.
  • 使用加权平均值和异型波器进行图像预处理.
  • 使用集成密集连接的挤压MobileNet v2 (Ef-DeSMob2) 进行特征提取.
  • 实现了与剩余金字塔深度分离可卷积神经网络 (SA:ResPyDSC) 的稀疏注意力进行分类.
  • 使用混合白白优化算法 (Hy-WBeOp) 微调的分类器超参数.

主要成果:

  • 实现了高精度 (98.06%),精度 (97.99%),回忆 (97.05%) 和F1得分 (96.08%).
  • 证明MSE (0.08),RMSE (0.27) 和MAE (0.21) 的错误率很低.
  • 在恶意软件分类的效率和准确性方面表现优于现有的技术.

结论:

  • 提出的深度学习方法有效地对云系统中的恶意软件进行分类.
  • 基于图像的API调用分析提高了检测可靠性并减少了错误.
  • 这种方法建立了一个强大的系统来保护自己免受复杂的网络威胁.