CHET: an optimizing compiler for fully-homomorphic neural-network inferencing

Dathathri, Roshan; Saarikivi, Olli; Chen, Hao; Laine, Kim; Lauter, Kristin; Maleki, Saeed; Musuvathi, Madanlal; Mytkowicz, Todd

doi:10.1145/3314221.3314628

Cited by 164 publications

(188 citation statements)

References 13 publications

Supporting

Mentioning

184

Contrasting

Unclassified

Order By: Relevance

“…Handwriting efficient HE kernels is a tedious and error-prone process as HE provides limited instructions, intra-ciphertext data movement must be done using vector rotation, and the noise budget adds additional sources of error. As a result, HE code is today is typically written by experts [16,27,40]. Figure 2.…”

Section: He Compilation Challengesmentioning

confidence: 99%

“…A nascent body of prior work exists and has investigated specific aspects of compiling HE code. For example, prior work has shown HE parameter tuning, which determines the noise budget, can be automated and optimized to improve performance [3,12,15,16]. Others have proposed mechanisms to optimize data layouts for neural networks [16].…”

Section: Introductionmentioning

confidence: 99%

“…For example, prior work has shown HE parameter tuning, which determines the noise budget, can be automated and optimized to improve performance [3,12,15,16]. Others have proposed mechanisms to optimize data layouts for neural networks [16]. Prior solutions have also used a mix of symbolic execution [3] and rewrite rules [7,12,15] for code generation and optimizations for logic minimization (e.g., Boolean logic minimization [12,28].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Porcupine: a synthesizing compiler for vectorized homomorphic encryption

Cowan

Dangwal

Alaghi

et al. 2021

Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation

View full text Add to dashboard Cite

Homomorphic encryption (HE) is a privacy-preserving technique that enables computation directly on encrypted data. Despite its promise, HE has seen limited use due to performance overheads and compilation challenges. Recent work has made significant advances to address the performance overheads but automatic compilation of efficient HE kernels remains relatively unexplored.This paper presents Porcupine, an optimizing compiler that generates vectorized HE code using program synthesis. HE poses three major compilation challenges: it only supports a limited set of SIMD-like operators, it uses long-vector operands, and decryption can fail if ciphertext noise growth is not managed properly. Porcupine captures the underlying HE operator behavior so that it can automatically reason about the complex trade-offs imposed by these challenges to generate optimized, verified HE kernels. To improve synthesis time, we propose a series of optimizations including a sketch design tailored to HE to narrow the program search space. We evaluate Porcupine using a set of kernels and show speedups of up to 52% (25% geometric mean) compared to heuristic-driven hand-optimized kernels. Analysis of Porcupine's synthesized code reveals that optimal solutions are not always intuitive, underscoring the utility of automated reasoning in this domain.

show abstract

Section: He Compilation Challengesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Porcupine: a synthesizing compiler for vectorized homomorphic encryption

Cowan

Dangwal

Alaghi

et al. 2021

Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation

View full text Add to dashboard Cite

show abstract

“…To predict the output value, we need to obtain β = [b (α • y) T ] T . Without decryption, we can obtain β by using matrix A, and the inner product between the kernel value and β induces the SVM function (9).…”

Section: Prediction Phasementioning

confidence: 99%

“…Using FHE, multiple institutes can share their data in an encrypted form and evaluate machine learning algorithms on them. Several works have been conducted on secure computations in machine learning algorithms with fully homomorphic encryptions: prediction phases [2]- [4] and training phases [5], [6] of the Logistic Regression Model (LRM), decision trees inference phases [7], and deep neural network inference phases [8], [9]. Notably, few works have been reported that propose private training for support vector machine (SVM) algorithms using FHE because the SVM training model has many constraints and non-polynomial functions.…”

Section: Introductionmentioning

confidence: 99%

HE-Friendly Algorithm for Privacy-Preserving SVM Training

et al. 2020

View full text Add to dashboard Cite

Support vector machine (SVM) is one of the most popular machine learning algorithms. It predicts a pre-defined output variable in real-world applications. Machine learning on encrypted data is becoming more and more important to protect both model information and data against various adversaries. While some studies have been proposed on inference or prediction phases, few have been reported on the training phase. Homomorphic encryption (HE) for the arithmetic of approximate numbers scheme enables efficient arithmetic evaluations of encrypted data of real numbers, which encourages to develop privacy-preserving machine learning training algorithm. In this study, we propose an HE-friendly algorithm for the SVM training phase which avoids inefficient operations and numerical instability on an encrypted domain. The inference phase is also implemented on the encrypted domain with fully-homomorphic encryption which enables real-time prediction. Our experiment showed that our HE-friendly algorithm outperformed the state-of-the-art logistic regression classifier with fully homomorphic encryption on toy and real-world datasets. To the best of our knowledge, this study is the first practical algorithm for training an SVM model with fully homomorphic encryption. Therefore, our result supports the development of practical applications of the privacy-preserving SVM model. INDEX TERMS Cryptography, data privacy, fully homomorphic encryption, support vector machine, privacy-preserving training.

show abstract

High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function

Lee

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

CHET: an optimizing compiler for fully-homomorphic neural-network inferencing

Cited by 164 publications

References 13 publications

Porcupine: a synthesizing compiler for vectorized homomorphic encryption

Porcupine: a synthesizing compiler for vectorized homomorphic encryption

HE-Friendly Algorithm for Privacy-Preserving SVM Training

High-Precision Bootstrapping of RNS-CKKS Homomorphic Encryption Using Optimal Minimax Polynomial Approximation and Inverse Sine Function

Contact Info

Product

Resources

About