Scholarlink

In the face of increasing cyber threats, this paper presents an AI-driven Random Forest algorithm specifically developed to detect Time-Based Blind SQL Injection attacks, with a focus on safeguarding Supervisory Control and Data Acquisition (SCADA) systems. SCADA systems play a crucial role in critical infrastructure, making their security paramount. By implementing this algorithm, the study aims to protect vital operational data and ensure the integrity and reliability of services. The algorithm, developed and tested using ML.NET, achieves an accuracy rate of 85%, outperforming the Gravince Boost algorithm, which recorded a 75% accuracy rate. These results highlight the efficacy of machine learning techniques in enhancing cybersecurity defenses. The paper advocates for a In-depth, multi-layered approach to critical infrastructure security, emphasizing the potential of machine learning technologies to mitigate sophisticated cyber threats.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Real-Time Detection of Time-Based Blind SQL Injection Using Machine Learning for Critical Infrastructure

  • 章节

  • 发表日期：

    2026年

查看全文
  • Venkatesh Mannuru,
  • Ali Al-Sinayyid,
  • Sasidhar Kadiyala,
  • Rohit Reddy Battula

摘要

In the face of increasing cyber threats, this paper presents an AI-driven Random Forest algorithm specifically developed to detect Time-Based Blind SQL Injection attacks, with a focus on safeguarding Supervisory Control and Data Acquisition (SCADA) systems. SCADA systems play a crucial role in critical infrastructure, making their security paramount. By implementing this algorithm, the study aims to protect vital operational data and ensure the integrity and reliability of services. The algorithm, developed and tested using ML.NET, achieves an accuracy rate of 85%, outperforming the Gravince Boost algorithm, which recorded a 75% accuracy rate. These results highlight the efficacy of machine learning techniques in enhancing cybersecurity defenses. The paper advocates for a In-depth, multi-layered approach to critical infrastructure security, emphasizing the potential of machine learning technologies to mitigate sophisticated cyber threats.