Downloads: 12 | Views: 91 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Informative Article | Computer Science | India | Volume 12 Issue 11, November 2023
Effective Impact of Intrusion Detection System for Manufacturing Industries Using Data Mining Techniques: A Comprehensive Study
Abstract: Intrusion detection systems are systems designed to monitor computer and network activities for security violations. These activities are observed by scrutinizing the audit data generated by the operating system or some other application programs running on the computer manufacturing industries have witnessed significant advancements in automation and connectivity, resulting in the proliferation of interconnected systems and devices. While this has increased efficiency and productivity, it has also exposed these industries to a growing risk of cyber-attacks and intrusions. Intrusion Detection Systems (IDS) play a crucial role in safeguarding manufacturing systems from unauthorized access and malicious activities. This paper presents an investigation into the use of data mining techniques to enhance the effectiveness of Intrusion Detection Systems in the context of manufacturing industries. Manufacturing environments are characterized by complex and heterogeneous data sources, making traditional rule-based IDS less effective in identifying novel and sophisticated attacks. Examples of security violations include the abuse of privileges or the use of attacks to exploit software or protocol vulnerabilities. Data mining techniques, such as machine learning algorithms and anomaly detection methods, offer the potential to address this challenge by learning from historical data and detecting previously unseen threats. This study explores the various data sources in manufacturing, including sensor data, network logs, and process data, and demonstrates how these can be integrated into a comprehensive IDS. The proposed approach is validated using real-world datasets and experimental results, showcasing its ability to effectively detect intrusions and anomalies in manufacturing systems. The integration of data mining techniques not only improves the accuracy of intrusion detection but also reduces false positives and enhances the adaptability of IDS to evolving threats.
Keywords: Data Mining, Knowledge discovery, Intrusion systems, Propagation, Data Warehousing, ADAM, neural network, MADAM, firewall network, Intrusion Detection Systems, Manufacturing Treats, Cyber-Attacks, Cyber-Threats, Cyber Security, Clustering Algorithms
Edition: Volume 12 Issue 11, November 2023,
Pages: 614 - 618