Application of big data technology in enterprise information security management.

Area of Science:

• Information Security
• Big Data Analytics
• Machine Learning

Background:

• Enterprise information security (EIS) faces evolving threats.
• Traditional security methods struggle with real-time risk identification.
• Big data technology (BDT) offers potential for advanced security solutions.

Purpose of the Study:

• To explore the application value of BDT in EIS.
• To develop a big data-driven risk prediction model for enterprises.
• To enhance enterprise information security protection capabilities.

Main Methods:

• Constructed a big data analysis system using complex network algorithms and machine learning.
• Employed feature engineering and model training for risk indicator extraction.
• Optimized model prediction performance for diverse security threats.

Main Results:

• The risk prediction model achieved an Area Under the Curve of 0.95.
• The model demonstrated high prediction accuracy and differentiation ability.
• Achieved an average precision of 0.87 in multi-class risk identification.

Conclusions:

• BDT is effective and feasible for EIS risk management.
• The developed prediction model significantly improves early warning accuracy and response speed.
• Provides strong technical support for enterprise information security protection.