Privacy-Preserving Big Data Architectures: AI-Driven Anomaly Detection and Homomorphic Encryption for Secure Data Processing
The rapid growth of big data has introduced significant privacy and security challenges. Traditional encryption methods often struggle to balance security with computational efficiency. This research explores AI-driven anomaly detection combined with homomorphic encryption (HE) to ensure secure and privacy-preserving big data processing. AI models enhance threat detection by identifying anomalies in encrypted datasets, while HE allows computations on encrypted data without decryption. Our experimental results demonstrate the feasibility of this approach, ensuring robust security while maintaining computational efficiency. Additionally, the study integrates aspects of Data Architecture, Business Intelligence, and Cloud Engineering to optimize data security and processing.
Keywords : Big Data, Privacy-Preserving, AI, Anomaly Detection, Homomorphic Encryption, Secure Computing, Data Architecture, Big Data Analyst, Data Scientist, Business Analysis, Data Security & Risk Management, Business Intelligence, Cloud Engineer, Cloud Architect, Data Engineer
