| 基于深度学习和信任度量的云平台自适应恶意攻击检测与响应算法 |
投稿时间：2024-01-29 修订日期：2024-04-07  点此下载全文 |
| 引用本文： |
| 摘要点击次数: 18 |
| 全文下载次数: 0 |
|
|
| 中文摘要:由于提取的云平台数据特征与异常行为相关性不高，导致云平台自适应恶意攻击检测效果不佳。因此，设计了基于深度学习和信任度量的云平台自适应恶意攻击检测与响应算法。利用传感器采集云平台数据，并对其进行平滑计算和规范化处理，再对其进行聚类分析，在深度学习网络的作用下，提取出云平台运行数据的多个特征，并计算其信任度值，通过计算自适应控制函数，构建恶意攻击检测模型，将检测结果作为基础，计算恶意攻击带来的风险值，由此设计恶意攻击响应机制。测试结果表明，以某云平台为实验对象，该算法在实际应用中检出率较高，检测效果较好。 |
| 中文关键词:深度学习 信任度量 云平台 恶意攻击 攻击响应 攻击检测算法 算法设计 |
| |
| Adaptive Malicious Attack Detection and Response Algorithm for Cloud Platforms Based on Deep Learning and Trust Metrics |
|
|
| Abstract:Due to the low correlation between the extracted cloud platform data features and abnormal behavior, the adaptive malicious attack detection effect of the cloud platform is poor. Therefore, a cloud platform adaptive malicious attack detection and response algorithm based on deep learning and trust metrics was designed. Utilizing sensors to collect cloud platform data, smoothing and normalizing it, and then performing cluster analysis on it. Under the influence of deep learning networks, multiple features of cloud platform operation data are extracted, and their trust values are calculated. By calculating adaptive control functions, a malicious attack detection model is constructed, and the detection results are used as the basis to calculate the risk value brought by malicious attacks, Design a malicious attack response mechanism based on this. The test results show that, taking a certain cloud platform as the experimental object, the algorithm has a high detection rate and good detection effect in practical applications. |
| keywords:Deep learning Trust measurement Cloud platform Malicious attacks Attack response Attack detection algorithm Algorithm design |
| 查看全文 查看/发表评论 下载pdf阅读器 |
位访问者,今日访问
