MLQENABLER: Enabling Secure Machine Learning Queries over Encrypted Database in Cloud Computing

2026-07-09

AI Summary

This work addresses the challenge of supporting efficient machine learning (ML) queries over encrypted databases in untrusted cloud environments. To bridge the gap between strong security guarantees and ML usability, the authors propose MLQENABLER, a novel framework that co-designs an encrypted database, a secure index structure, and a query protocol. This approach enables direct execution of ML operations on ciphertext for the first time without compromising security. By overcoming the fundamental incompatibility between conventional encryption schemes and ML computation, MLQENABLER achieves a practical balance between confidentiality and functionality. Experimental evaluation demonstrates that the system incurs only modest performance overhead while maintaining an acceptable level of security, thereby offering a viable solution for privacy-preserving ML in outsourced settings.

Abstract

In cloud computing, the public cloud service providers (CSPs) can provide cloud storage as the primary service while providing additional machine learning (ML)-based services by using the clients' data in storage. This business model extends the border of cloud computing services and brings in new business growth possibilities. Although it is promising, the model also brings in security concerns since the public commercial cloud cannot be fully trusted. For example, the public commercial clouds may sell clients' sensitive data to the government or other companies. To address the security concerns, an immediate solution is to require clients to encrypt their datasets before outsourcing to the cloud. However, if a database is formally encrypted, then the database contains only pseudorandom numbers, making it impossible to enable ML over it. In this project, we propose MLQENABLER (ML Queries Enabler) scheme to enable secure ML queries over encrypted database in cloud storage. MLQENABLER employs an index-aid approach to achieve security and ML capability simultaneously. Our initial experiments show that MLQENABLER achieves an acceptable security level while incurring only a slight ML performance degradation.

Problem

• secure machine learning
• encrypted database
• cloud computing
• ML queries
• data privacy

Innovation

• secure machine learning
• encrypted database
• index-aided encryption
• cloud computing
• privacy-preserving ML