NSHEDB: Noise-Sensitive Homomorphic Encrypted Database Query Engine

TL;DR

NSHEDB is presented, a secure query processing engine designed to address challenges at the system architecture level and achieves 20x-V1370x speedup and a 73x storage reduction compared to state-of-the-art HE-based systems, while upholding 128-bit security in a semi-honest model with no key release or trusted components.

Abstract

Homomorphic encryption (HE) enables computations directly on encrypted data, offering strong cryptographic guarantees for secure and privacy-preserving data storage and query execution. However, despite its theoretical power, practical adoption of HE in database systems remains limited due to extreme cipher-text expansion, memory overhead, and the computational cost of bootstrapping, which resets noise levels for correctness. This paper presents NSHEDB, a secure query processing engine designed to address these challenges at the system architecture level. NSHEDB uses word-level leveled HE (LHE) based on the BFV scheme to minimize ciphertext expansion and avoid costly bootstrapping. It introduces novel techniques for executing equality, range, and aggregation operations using purely homomorphic computation, without transciphering between different HE schemes (e.g., CKKS/BFV/TFHE) or relying on trusted hardware. Additionally, it incorporates a noise-aware query planner to extend computation depth while preserving security guarantees. We implement and evaluate NSHEDB on real-world database workloads (TPC-H) and show that it achieves 20x-V1370x speedup and a 73x storage reduction compared to state-of-the-art HE-based systems, while upholding 128-bit security in a semi-honest model with no key release or trusted components.

Figures (7)

• Figure 1: The system overview of NSHEDB
• Figure 2: The process of JOIN in NSHEDB
• Figure 3: Noise optimization example. Plan (b) executes the SELECT and JOIN operators independently and then intersects their outputs, saving roughly one equality check in multiplicative depth compared with the sequential execution in plan (a).
• Figure 4: Speedup for basic database operations on NSHEDB compared to baselines. NSHEDB achieves speedups up to 3,148$\times$ over HE$^3$DB.
• Figure 5: NSHEDB's Multi-threaded Performance. It achieves a speedup of 1.74$\times$, 2.73$\times$, and 4.11$\times$ with 2, 4, and 8 threads.