Adaptability of data security in a changing environment: a strategy based on artificial intelligence
Anassin Chiatsé Mireille Patricia · 2025
In a context where data security is a crucial issue for companies, especially with the rise of changing environments, this article explores the use of artificial intelligence and machine learning algorithms to improve data protection. We use two models, Random Forest and Support Vector Machine (SVM), to detect anomalies in data flows in real time and optimize security parameters. The proposed method combines data extraction and transformation techniques with machine learning models capable of detecting potential threats and adjusting security measures dynamically. Thanks to this approach, we were able not only to improve the accuracy and speed of security systems, but also to reduce query response times and optimize the use of storage resources. The results obtained show that the Random Forest model is particularly effective in this context, offering better performance in terms of precision (94.7%) and recall (92.1%), compared to the SVM model which, although effective on small datasets, proves less suited to the large volumes of data often encountered in cloud computing infrastructures.