Mp2ml

Boemer, Fabian; Cammarota, Rosario; Demmler, Daniel; Schneider, Thomas; Yalame, Hossein

doi:10.1145/3407023.3407045

Cited by 34 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This adjustment enables PPNN models to undergo homomorphic evaluation of the softmax function directly on the server, enhancing the security. Following this, Boemer et al [13] argued that relying solely on the softmax function is insufficient for providing effective model protection. They advocated for the replacement of the softmax function with the argmax function.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Homomorphic Argmax Approximation for Privacy-Preserving Neural Networks

Zhang,

Duan,

2024

Cryptography

View full text Add to dashboard Cite

Privacy-preserving neural networks offer a promising solution to train and predict without user privacy leakage, and fully homomorphic encryption (FHE) stands out as one of the key technologies, as it enables homomorphic operations over encrypted data. However, only addition and multiplication homomorphisms are supported by FHE, and thus, it faces huge challenges when implementing non-linear functions with ciphertext inputs. Among the non-linear functions in neural networks, one may refer to the activation function, the argmax function, and maximum pooling. Inspired by using a composition of low-degree minimax polynomials to approximate sign and argmax functions, this study focused on optimizing the homomorphic argmax approximation, where argmax is a mathematical operation that identifies the index of the maximum value within a given set of values. For the method that uses compositions of low-degree minimax polynomials to approximate argmax, in order to further reduce approximation errors and improve computational efficiency, we propose an improved homomorphic argmax approximation algorithm that includes rotation accumulation, tree-structured comparison, normalization, and finalization phases. And then, the proposed homomorphic argmax algorithm was integrated into a neural network structure. Comparative experiments indicate that the network with our proposed argmax algorithm achieved a slight increase in accuracy while significantly reducing the inference latency by 58%, as the homomorphic sign and rotation operations were rapidly reduced.

show abstract

Section: Related Workmentioning

confidence: 99%

An Efficient Homomorphic Argmax Approximation for Privacy-Preserving Neural Networks

Zhang,

Duan,

2024

Cryptography

View full text Add to dashboard Cite

show abstract

“…2) Cryptography Based Privacy-Preserving: Cryptography-based methods can satisfy the invisibility and lossless of the result accuracy. Commonly used methods include secure multi-party computation (MPC) [44], [45] and homomorphic encryption (HE) [34], [46]. But partial homomorphic encryption can only support one kind of operation, the additive or multiplicative.…”

Section: A Privacy-preserving Deep-learning Inferencementioning

confidence: 99%

A Generic Cryptographic Deep-Learning Inference Platform for Remote Sensing Scenes

Chen

Wang

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deep learning plays an essential role in multidisciplinary research of Remote sensing. We will encounter security problems during the data acquisition, processing, and result generation stages. Therefore, secure deep-learning inference services are one of the most important links. Some theoretical progress has been made in cryptographic deep-learning inference, but it lacks a general platform that can be realized in reality. Constantly modifying the corresponding models to approximate the plaintext results reveal the model information to a certain extent. This paper proposes a generic post-quantum platform named the PyHENet, which perfectly combines cryptography with plaintext deep learning libraries. Secondly, we optimize the convolution, activation, and pooling functions and complete the ciphertext operation under floating point numbers for the first time. Moreover, the computation process is accelerated by SIMD and GPU parallel computing. The experimental results show that the PyHENet is closer to the plaintext inference platform than any other cryptographic model and has satisfactory robustness. The optimized PyHENet obtained a better accuracy of 95.05% in the high-resolution NaSC-TG2 database, which the Tiangong-2 space station received.

show abstract

“…A series of recent works have made encouraging progress towards improving system efficiency of privacy-preserving MLaaS (Demmler, Schneider, and Zohner 2015;Liu et al 2017;Mohassel and Zhang 2017;Juvekar, Vaikuntanathan, and Chandrakasan 2018;Riazi et al 2018;Rouhani, Riazi, and Koushanfar 2018;Mohassel and Rindal 2018;Riazi et al 2019;Mishra et al 2020;Rathee et al 2020;Boemer et al 2020;Zhang, Xin, and Wu 2021;Patra et al 2021;Tan et al 2021;Hussain et al 2021;Ng et al 2021;Huang et al 2022). Among them, the mixed-primitive frameworks which utilize HE to compute linear functions (e.g., convolution and fully connection) while adopt MPC for nonlinear functions (e.g., ReLU) have demonstrated additional efficiency advantages (Liu et al 2017;Juvekar, Vaikuntanathan, and Chandrakasan 2018;Rathee et al 2020;Huang et al 2022) and it is noteworthy that the inference speed has been improved…”

Section: Introductionmentioning

confidence: 99%

United We Stand: Accelerating Privacy-Preserving Neural Inference by Conjunctive Optimization with Interleaved Nexus

Zhang,

Xiang,

Xin

et al. 2024

AAAI

View full text Add to dashboard Cite

Privacy-preserving Machine Learning as a Service (MLaaS) enables the powerful cloud server to run its well-trained neural model upon the input from resource-limited client, with both of server's model parameters and client's input data protected. While computation efficiency is critical for the practical implementation of privacy-preserving MLaaS and it is inspiring to witness recent advances towards efficiency improvement, there still exists a significant performance gap to real-world applications. In general, state-of-the-art frameworks perform function-wise efficiency optimization based on specific cryptographic primitives. Although it is logical, such independent optimization for each function makes noticeable amount of expensive operations unremovable and misses the opportunity to further accelerate the performance by jointly considering privacy-preserving computation among adjacent functions. As such, we propose COIN: Conjunctive Optimization with Interleaved Nexus, which remodels mainstream computation for each function to conjunctive counterpart for composite function, with a series of united optimization strategies. Specifically, COIN jointly computes a pair of consecutive nonlinear-linear functions in the neural model by reconstructing the intermediates throughout the whole procedure, which not only eliminates the most expensive crypto operations without invoking extra encryption enabler, but also makes the online crypto complexity independent of filter size. Experimentally, COIN demonstrates 11.2x to 29.6x speedup over various function dimensions from modern networks, and 6.4x to 12x speedup on the total computation time when applied in networks with model input from small-scale CIFAR10 to large-scale ImageNet.

show abstract

Mp2ml

Cited by 34 publications

References 34 publications

An Efficient Homomorphic Argmax Approximation for Privacy-Preserving Neural Networks

An Efficient Homomorphic Argmax Approximation for Privacy-Preserving Neural Networks

A Generic Cryptographic Deep-Learning Inference Platform for Remote Sensing Scenes

United We Stand: Accelerating Privacy-Preserving Neural Inference by Conjunctive Optimization with Interleaved Nexus

Contact Info

Product

Resources

About