Vol. 10 No. 01 (2025): Volume 10 Issue 01

This study investigates the use of artificial intelligence (AI) and machine learning (ML) models to predict, detect, and mitigate cybersecurity threats, including zero-day attacks, ransomware, and insider threats. Using a comprehensive dataset of network logs and attack signatures, we evaluated models such as Logistic Regression, Random Forest, XGBoost, CNN, and LSTMOur results demonstrate that deep learning models, particularly CNN (97.3% AUC-ROC) and LSTM (96.8% AUC-ROC), significantly outperform traditional methods, excelling in real-time threat detection and minimizing false positives. This study highlights the practical applicability of AI and ML in enhancing cybersecurity frameworks, paving the way for more efficient and scalable solutions against evolving threats.

With the increasing adoption of cloud computing, ensuring data privacy and security has become a critical challenge, particularly in the context of anomaly detection. This study proposes a lightweight homomorphic encryption-based approach to enhance cloud security by enabling privacy-preserving anomaly detection. Homomorphic encryption allows computations to be performed on encrypted data without the need for decryption, ensuring that sensitive information remains protected throughout the detection process. The paper explores the implementation of a lightweight encryption scheme that balances both computational efficiency and strong security, making it suitable for real-time anomaly detection in cloud environments. The proposed method is evaluated against traditional encryption approaches, demonstrating its capability to detect anomalous behaviors without exposing raw data to cloud service providers. Results indicate that the lightweight homomorphic encryption method maintains high levels of accuracy in detecting anomalies while ensuring minimal performance overhead, making it a promising solution for secure cloud-based anomaly detection systems. This work contributes to advancing privacy-preserving techniques in cloud security and paves the way for more secure and efficient cloud computing applications.