PPPQ-ANN is a hybrid FHE+TEE framework with product quantization that generates databases in under 2 hours and delivers over 50 QPS on million-scale datasets while preserving privacy.
Somewhat practical fully homomorphic encryption
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper introduces a symmetric FHE construction using plaintext fragmentation, dynamic interposition, exponent and coefficient regulators, and a binding mechanism to manage noise and protect the secret key.
citing papers explorer
-
Privacy-Preserving Product-Quantized Approximate Nearest Neighbor Search Framework for Large-scale Datasets via A Hybrid of Fully Homomorphic Encryption and Trusted Execution Environment
PPPQ-ANN is a hybrid FHE+TEE framework with product quantization that generates databases in under 2 hours and delivers over 50 QPS on million-scale datasets while preserving privacy.
-
Beyond Controlled Noise: Achieving Symmetric FHE through Dynamic Position Shifting
The paper introduces a symmetric FHE construction using plaintext fragmentation, dynamic interposition, exponent and coefficient regulators, and a binding mechanism to manage noise and protect the secret key.