Ai-Powered Dual Server Public-Key Encryption for Secure Cloud Search

The concept of dual-server and multi-party searchable encryption strengthens traditional Keyword search combined with public-key encryption (PEKS), which is otherwise prone to keyword guessing threats, especially insider-based attacks. Instead of relying on a single server, the use of two independent servers along with cryptographic primitives like smooth projective hash functions makes it harder for adversaries to infer searched terms. These frameworks also extend to multi-user and hierarchical access, ensuring flexible and fine-grained data control. Moreover, privacy-preserving multi-keyword techniques allow users to perform combined (AND/OR) queries without exposing keyword usage patterns or statistics. To further enhance practicality, ranked retrieval schemes integrate orderpreserving encryption with symmetric approaches, enabling secure and efficient top-k results. In addition, the integration of artificial intelligence (AI) models has been explored to improve keyword matching, relevance ranking, and adaptability in encrypted search systems.