# Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference Source: [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference]() Collection index: [llms.txt]() Data updated: 2025-10-27T05:56:48.736Z Authors: Edward Chou, Josh Beal, Daniel Levy, Serena Yeung, Albert Haque, Li Fei-Fei Published: 2018-11-25T05:56:18.000Z ## Abstract Homomorphic encryption enables arbitrary computation over data while it remains encrypted. This privacy-preserving feature is attractive for machine learning, but requires significant computational time due to the large overhead of the encryption scheme. We present Faster CryptoNets, a method for efficient encrypted inference using neural networks. We develop a pruning and quantization approach that leverages sparse representations in the underlying cryptosystem to accelerate inference. We derive an optimal approximation for popular activation functions that achieves maximally-sparse encodings and minimizes approximation error. We also show how privacy-safe training techniques can be used to reduce the overhead of encrypted inference for real-world datasets by leveraging transfer learning and differential privacy. Our experiments show that our method maintains competitive accuracy and achieves a significant speedup over previous methods. This work increases the viability of deep learning systems that use homomorphic encryption to protect user privacy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [ReLU Approximation on SST-2 DistilBERT tokenized vectors (test)](): ReLU approximation; SST-2 DistilBERT tokenized vectors (test); MSE: 0.024. - [Image Classification on MNIST CKKS (encrypted)](): Image Classification; MNIST CKKS (encrypted); Total Exp. Time (s): 1917.99. - [ReLU Approximation on SST-2 RoBERTa tokenized vectors (test)](): ReLU approximation; SST-2 RoBERTa tokenized vectors (test); MSE: 0.037. - [Image Classification on MNIST (Plaintext and Encrypted Accuracy)](): Image Classification; MNIST; Plaintext Accuracy: 97.3. - [Image Classification on CIFAR-100 (ACC, NLL, ECE, ESS)](): Image Classification; CIFAR-100; Accuracy: 37.7. - [Image Classification on CIFAR-10 (Accuracy)](): Image Classification; CIFAR-10; Accuracy: 64.2. ## Original sources and implementation [Original paper]() [PDF]()