Survey on Fully Homomorphic Encryption, Theory, and Applications

Proceedings of the IEEE, Journal Year: 2022, Volume and Issue: 110(10), P. 1572 - 1609

Published: Oct. 1, 2022

Data privacy concerns are increasing significantly in the context of Internet Things, cloud services, edge computing, artificial intelligence applications, and other applications enabled by next-generation networks. Homomorphic encryption addresses challenges enabling multiple operations to be performed on encrypted messages without decryption. This article comprehensively homomorphic from both theoretical practical perspectives. delves into mathematical foundations required understand fully ( $\textsf {FHE}$ ). It consequently covers design fundamentals security properties describes main schemes based various problems. On a more level, this presents view privacy-preserving machine learning using then surveys at length an engineering angle, covering potential application fog computing services. also provides comprehensive analysis existing state-of-the-art libraries tools, implemented software hardware, performance thereof.

Language: Английский

---

BTS

Published: May 31, 2022

Homomorphic encryption (HE) enables the secure offloading of computations to cloud by providing computation on encrypted data (ciphertexts). HE is based noisy schemes in which noise accumulates as more are applied data. The limited number operations applicable prevents practical applications from exploiting HE. Bootstrapping an unlimited or fully (FHE) refreshing ciphertext. Unfortunately, bootstrapping requires a significant amount additional and memory bandwidth well. Prior works have proposed hardware accelerators for primitives FHE. However, best our knowledge, this first propose FHE accelerator that supports first-class citizen.

Language: Английский

---

Blockchain-Based Privacy-Enhancing Federated Learning in Smart Healthcare: A Survey

Blockchains, Journal Year: 2025, Volume and Issue: 3(1), P. 1 - 1

Published: Jan. 1, 2025

Federated learning (FL) has emerged as an efficient machine (ML) method with crucial privacy protection features. It is adapted for training models in Internet of Things (IoT)-related domains, including smart healthcare systems (SHSs), where the introduction IoT devices and technologies can arise various security concerns. However, FL cannot solely address all challenges, privacy-enhancing (PETs) blockchain are often integrated to enhance frameworks within SHSs. The critical questions remain regarding how these they contribute enhancing This survey addresses by investigating recent advancements on combination PETs healthcare. First, this emphasizes integration into context. Second, challenge integrating FL, it examines three main technical dimensions such blockchain-enabled model storage, aggregation, gradient upload frameworks. further explores collectively ensure integrity confidentiality data, highlighting their significance building a trustworthy SHS that safeguards sensitive patient information.

Language: Английский

---

ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse

Published: Oct. 1, 2022

Homomorphic Encryption (HE) is one of the most promising post-quantum cryptographic schemes that enable privacy-preserving computation on servers. However, noise accumulates as we perform operations HE-encrypted data, restricting number possible operations. Fully HE (FHE) removes this restriction by introducing bootstrapping operation, which refreshes data; however, FHE are highly memory-bound. Bootstrapping, in particular, requires loading GBs evaluation keys and plaintexts from offchip memory, makes acceleration fundamentally bottlenecked off-chip memory bandwidth.In paper, propose ARK, an Accelerator for with Runtime data generation inter-operation Key reuse. ARK enables practical workloads a novel algorithm-architecture co-design to accelerate bootstrapping. We first eliminate bandwidth bottleneck through runtime key This approach fully exploit on-chip substantially reducing size working set. On top such algorithmic enhancements, build microarchitecture minimizes movement efficient, alternating distribution policy based access patterns streamlined dataflow organization tailored functional units – including base conversion, number-theoretic transform, automorphism units. Overall, our codesign effectively handles heavy overheads FHE, drastically cost operations,

Language: Английский

---

A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 117477 - 117500

Published: Jan. 1, 2022

Outsourced computation for neural networks allows users access to state-of-the-art models without investing in specialized hardware and know-how. The problem is that the lose control over potentially privacy-sensitive data. With homomorphic encryption (HE), a third party can perform on encrypted data revealing its content. In this paper, we reviewed scientific articles publications particular area of Deep Learning Architectures Privacy-Preserving Machine (PPML) with Fully HE. We analyzed changes network architectures make them compatible HE how these impact performance. Next, find numerous challenges HE-based privacy-preserving deep learning, such as computational overhead, usability, limitations posed by schemes. Furthermore, discuss potential solutions PPML challenges. Finally, propose evaluation metrics allow better more meaningful comparison solutions.

Language: Английский

---

Preserving data privacy in machine learning systems

Computers & Security, Journal Year: 2023, Volume and Issue: 137, P. 103605 - 103605

Published: Nov. 29, 2023

The wide adoption of Machine Learning to solve a large set real-life problems came with the need collect and process volumes data, some which are considered personal sensitive, raising serious concerns about data protection. Privacy-enhancing technologies (PETs) often indicated as solution protect achieve general trustworthiness required by current EU regulations on protection AI. However, an off-the-shelf application PETs is insufficient ensure high-quality protection, one needs understand. This work systematically discusses risks against in modern systems taking original perspective owners, who those hold various sets, models, or both, throughout machine learning life cycle considering different architectures. It argues that origin threats, level offered depend processing phase, role parties involved, architecture where deployed. By offering framework discuss privacy confidentiality for owners identifying assessing privacy-preserving countermeasures learning, this could facilitate discussion compliance directives. We challenges research questions still unsolved field. In respect, paper provides researchers developers working comprehensive body knowledge let them advance science field well closely related fields such Artificial Intelligence.

Language: Английский

---

Optimized Privacy-Preserving CNN Inference With Fully Homomorphic Encryption

IEEE Transactions on Information Forensics and Security, Journal Year: 2023, Volume and Issue: 18, P. 2175 - 2187

Published: Jan. 1, 2023

Inference of machine learning models with data privacy guarantees has been widely studied as concerns are getting growing attention from the community. Among others, secure inference based on Fully Homomorphic Encryption (FHE) proven its utility by providing stringent at sometimes affordable cost. Still, previous work was restricted to shallow and narrow neural networks simple tasks due high computational cost incurred FHE. In this paper, we propose a more efficient way evaluating convolutions FHE, where remains constant regardless kernel size, resulting in 12–46× timing improvement various sizes. Combining our methods FHE bootstrapping, achieve least 18.9% (and 48.1%) reduction homomorphic evaluation 20-layer CNN classifiers part it) CIFAR10/100 ImageNet, respectively) datasets. Furthermore, consideration being effective for CNNs intensive convolutional operations exploring such CNNs, 5× faster than prior works having same or less accuracy.

Language: Английский

---

HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data

Proceedings on Privacy Enhancing Technologies, Journal Year: 2023, Volume and Issue: 2023(1), P. 325 - 342

Published: Jan. 1, 2023

Privacy-preserving solutions enable companies to offload confidential data third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE), which allows performing computation on encrypted data. Most HE schemes work in a SIMD fashion, and the packing method can dramatically affect running time memory costs. Finding that leads an optimal performant implementation is hard task. We present simple intuitive framework abstracts decision for user. explain its underlying structures optimizer, propose novel algorithm 2D convolution operations. used this implement HE-friendly version of AlexNet, runs three minutes, several orders magnitude faster than other state-of-the-art only use HE.

Language: Английский

---

Privacy preservation in Artificial Intelligence and Extended Reality (AI-XR) metaverses: A survey

Journal of Network and Computer Applications, Journal Year: 2024, Volume and Issue: 231, P. 103989 - 103989

Published: Aug. 2, 2024

The metaverse is a nascent concept that envisions virtual universe, collaborative space where individuals can interact, create, and participate in wide range of activities. Privacy the critical concern as evolves immersive experiences become more prevalent. privacy problem refers to challenges concerns surrounding personal information data within Virtual Reality (VR) environments shared VR becomes accessible. Metaverse will harness advancements from various technologies such Artificial Intelligence (AI), Extended (XR) Mixed (MR) provide personalized services its users. Moreover, enable experiences, relies on collection fine-grained user leads issues. Therefore, before potential be fully realized, related must addressed. This includes safeguarding users' control over their data, ensuring security information, protecting in-world actions interactions unauthorized sharing. In this paper, we explore future metaverses are expected face, given reliance AI for tracking users, creating XR MR facilitating interactions. thoroughly analyze technical solutions differential privacy, Homomorphic Encryption, Federated Learning discuss sociotechnical issues regarding privacy.

Language: Английский

---

SoK: Fully Homomorphic Encryption Accelerators

ACM Computing Surveys, Journal Year: 2024, Volume and Issue: 56(12), P. 1 - 32

Published: July 5, 2024

Fully Homomorphic Encryption (FHE) is a key technology enabling privacy-preserving computing. However, the fundamental challenge of FHE its inefficiency, due primarily to underlying polynomial computations with high computation complexity and extremely time-consuming ciphertext maintenance operations. To tackle this challenge, various accelerators have recently been proposed by both research industrial communities. This article takes first initiative conduct systematic study on 14 accelerators: cuHE/cuFHE, nuFHE, HEAT, HEAX, HEXL, HEXL-FPGA, 100×, F1, CraterLake, BTS, ARK, Poseidon, FAB, TensorFHE. We make our observations evolution trajectory these existing establish qualitative connection between them. Then, we perform testbed evaluations representative open-source provide quantitative comparison Finally, insights learned from studies, discuss potential directions inform future design implementation for accelerators.

Language: Английский

---