HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
This work addresses the challenge of slow inference times for privacy-preserving neural networks, which is critical for applications requiring secure data processing, but it is incremental as it optimizes an existing approach rather than introducing a new paradigm.
The paper tackled the problem of inefficient inference latency in privacy-preserving neural networks (PPNNs) using homomorphic encryption by proposing HEMET, a mobile architecture designed to reduce multiplicative depth, resulting in a 59.3% to 61.2% reduction in inference latency and a 0.4% to 0.5% improvement in accuracy compared to state-of-the-art methods.
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 such as SqueezeNet for smaller computing overhead, but we find naïvely using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a \textbf{HE}-friendly privacy-preserving \textbf{M}obile neural n\textbf{ET}work architecture, \textbf{HEMET}. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by $59.3\%\sim 61.2\%$, and improves the inference accuracy by $0.4 \% \sim 0.5\%$.