CryptoGRU: Low Latency Privacy-Preserving Text Analysis With GRU

2020-10-22 · EMNLP 2021 11 · Bo Feng, Qian Lou, Lei Jiang, Geoffrey C. Fox

Billions of text analysis requests containing private emails, personal text messages, and sensitive online reviews, are processed by recurrent neural networks (RNNs) deployed on public clouds every day. Although prior secure networks combine homomorphic encryption (HE) and garbled circuit (GC) to preserve users' privacy, naively adopting the HE and GC hybrid technique to implement RNNs suffers from long inference latency due to slow activation functions. In this paper, we present a HE and GC hybrid gated recurrent unit (GRU) network, CryptoGRU, for low-latency secure inferences. CryptoGRU replaces computationally expensive GC-based $tanh$ with fast GC-based $ReLU$, and then quantizes $sigmoid$ and $ReLU$ with a smaller bit length to accelerate activations in a GRU. We evaluate CryptoGRU with multiple GRU models trained on 4 public datasets. Experimental results show CryptoGRU achieves top-notch accuracy and improves the secure inference latency by up to $138\times$ over one of state-of-the-art secure networks on the Penn Treebank dataset.

📄 PDF Abstract BibTeX arXiv:2010.11796

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Methods 이 논문이 사용한 방법론

GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…

HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture

2021-05-31 · Qian Lou, Lei Jiang

Recently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures s…

Privacy Preserving

Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity

2026-06-23 · Yuanhe Zhao, Tianyu Zhang, Huafei Xing, Derek F. Wong 외 arxiv

Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts. To address this, we propose a multi-…

Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC

2024-07-24 · Ke Lin, Yasir Glani, Ping Luo

Secure multi-party computation (MPC) facilitates privacy-preserving computation between multiple parties without leaking private information. While most secure deep learning techniques utilize MPC operations to achieve f…

Deep Learning Privacy Preserving Privacy Preserving Deep Learning

Efficient Privacy-Preserving KAN Inference Using Homomorphic Encryption

2024-09-12 · Zhizheng Lai, Yufei Zhou, Peijia Zheng, Lin Chen

The recently proposed Kolmogorov-Arnold Networks (KANs) offer enhanced interpretability and greater model expressiveness. However, KANs also present challenges related to privacy leakage during inference. Homomorphic enc…

image-classification Image Classification Kolmogorov-Arnold Networks Privacy Preserving

PrivLLMSwarm: Privacy-Preserving LLM-Driven UAV Swarms for Secure IoT Surveillance

2025-12-07 · Jifar Wakuma Ayana, Huang Qiming arxiv

Large Language Models (LLMs) are emerging as powerful enablers for autonomous reasoning and natural-language coordination in unmanned aerial vehicle (UAV) swarms operating within Internet of Things (IoT) environments. Ho…

Reinforcement Learning Federated Learning