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

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

Target-driven machine learning-enabled virtual screening (TAME-VS) enables prioritization of AKR1C3 inhibitors.

Communications chemistry·2026
Same author

An EGFR-directed photoimmunotheranostic conjugate enables tumor-specific imaging and potent synergistic antitumor activity.

Journal of photochemistry and photobiology. B, Biology·2026
Same author

Seasonal Dynamics of the Gut Microbiome and Functional Adaptations in Sika Deer (<i>Cervus nippon kopschi</i>).

Animals : an open access journal from MDPI·2026
Same author

Stereodefined Improbable [3]Rotaxane by Post-Interlocking Ring Editing.

Angewandte Chemie (International ed. in English)·2026
Same author

Bio-Inspired Neural Network Dynamics-Aware Reinforcement Learning for Spiking Neural Network.

Biomimetics (Basel, Switzerland)·2026
Same author

Classification of Point Cloud Data in Road Scenes Based on PointNet+.

Sensors (Basel, Switzerland)·2026

相关实验视频

Updated: May 31, 2025

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

455

MalHAPGNN:一个基于呼叫图的增强式恶意软件检测框架,使用分层注意力聚合图形神经网络.

Wenjie Guo1, Wenbiao Du1, Xiuqi Yang1

  • 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100811, China.

Sensors (Basel, Switzerland)
|January 25, 2025
PubMed
概括
此摘要是机器生成的。

这项研究介绍了MalHAPGNN,这是一种用于恶意软件检测的新型深度学习框架. 它通过增强的调用图形和BERT增强了功能嵌入,优于现有的图形神经网络方法.

关键词:
图表神经网络的神经网络图形聚合机制 图形聚合机制恶意软件检测 恶意软件检测嵌入式恶意软件嵌入式恶意软件代表性学习学习学习

更多相关视频

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

363

相关实验视频

Last Updated: May 31, 2025

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

455
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

363

科学领域:

  • 计算机科学 计算机科学
  • 网络安全 网络安全
  • 人工智能的人工智能

背景情况:

  • 恶意软件检测中的深度学习经常错过语义和结构特征.
  • 现有的方法专注于表面特征,缺乏深入分析.

研究的目的:

  • 介绍MalHAPGNN,一种用于增强恶意软件检测的新框架.
  • 为了解决当前基于神经网络的恶意软件功能嵌入的局限性.

主要方法:

  • 利用一个分层的注意力聚合图神经网络 (GNN) 与增强的呼叫图.
  • 使用来自变压器的双向编码器表示 (BERT) 来进行属性增强的函数嵌入.
  • 综合功能节点采样和结构性学习策略.

主要成果:

  • MalHAPGNN提供了一份跨语义,语法和结构维度的恶意代码的全面概况.
  • 对Kaggle和VirusShare数据集的实验显示,与其他基于GNN的方法相比,性能优越.

结论:

  • 在恶意软件检测能力方面,MalHAPGNN提供了显著的进步.
  • 该框架有效地捕获了深层次的语义和结构信息,以提高准确性.