Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 30039 - 30054

Published: Jan. 1, 2022

Fully homomorphic encryption (FHE) is a prospective tool for privacy-preserving machine learning (PPML). Several PPML models have been proposed based on various FHE schemes and approaches. Although are suitable as tools implementing models, previous FHE, such CryptoNet, SEALion, CryptoDL, limited to simple nonstandard types of models; they not proven be efficient accurate with more practical advanced datasets. Previous replaced non-arithmetic activation functions arithmetic instead adopting approximation methods did use bootstrapping, which enables continuous evaluations. Thus, could neither standard nor employ large numbers layers. In this work, we first implement the ResNet-20 model RNS-CKKS bootstrapping verify implemented CIFAR-10 dataset plaintext parameters. Instead replacing functions, state-of-the-art evaluate these ReLU Softmax, sufficient precision. Further, time, technique scheme in model, us an arbitrary deep encrypted data. We numerically that shows 98.43% identical results original non-encrypted The classification accuracy 92.43%±2.65%, quite close CNN (91.89%). It takes approximately 3 h inference dual Intel Xeon Platinum 8280 CPU (112 cores) 172 GB memory. believe opens possibility applying model.

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

---

On the Precision Loss in Approximate Homomorphic Encryption

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 325 - 345

Published: Jan. 1, 2024

Language: Английский

---

SHARP: A Short-Word Hierarchical Accelerator for Robust and Practical Fully Homomorphic Encryption

Published: June 16, 2023

Fully homomorphic encryption (FHE) is an emerging cryptographic technology that guarantees the privacy of sensitive user data by enabling direct computations on encrypted data. Despite security benefits this approach, FHE associated with prohibitively high levels computational and memory overhead, preventing its widespread use in real-world services. Numerous domain-specific hardware designs have been proposed to address issue, but most them excessive amounts chip area power, leaving room for further improvements terms practicality.

Language: Английский

---

Accelerating BGV Bootstrapping for Large p Using Null Polynomials over $$\mathbb {Z}_{p^e}$$

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 403 - 432

Published: Jan. 1, 2024

Language: Английский

---

Precise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Data

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 62062 - 62076

Published: Jan. 1, 2023

Homomorphic encryption (HE) is one of the representative solutions to privacy-preserving machine learning (PPML) classification enabling server classify private data clients while guaranteeing privacy. This work focuses on PPML using word-wise fully homomorphic (FHE). In order implement deep HE, ReLU and max-pooling functions should be approximated by polynomials for operations. Most previous studies focus HE-friendly networks, which approximate low-degree polynomials. However, this approximation cannot support deeper neural networks due large errors in general can only relatively small datasets. Thus, we propose a precise polynomial technique, composition minimax low degrees functions. If replace with proposed polynomials, standard models such as ResNet VGGNet still used without further modification FHE. Even pre-trained parameters retraining, makes method more practical. We ResNet-152 15, 27, 29. Then, succeed classifying plaintext ImageNet dataset 77.52% accuracy, very close original model accuracy 78.31%. Also, obtain an 87.90% encrypted CIFAR-10 ResNet-20 any additional training.

Language: Английский

---

Bootstrapping for BGV and BFV Revisited

Journal of Cryptology, Journal Year: 2023, Volume and Issue: 36(2)

Published: March 23, 2023

Language: Английский

---

Scalable and Privacy-Preserving Federated Principal Component Analysis

2022 IEEE Symposium on Security and Privacy (SP), Journal Year: 2023, Volume and Issue: unknown

Published: May 1, 2023

Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the problem of performing a federated PCA on private distributed among multiple providers while ensuring confidentiality. Our solution, SF-PCA, end-to-end secure system that preserves confidentiality both original and all intermediate results passive-adversary model with up to all-but-one colluding parties. SF-PCA jointly leverages multiparty homomorphic encryption, interactive protocols, edge computing efficiently interleave computations local cleartext operations collectively encrypted data. obtains as accurate non-secure centralized solutions, independently distribution It scales linearly or better dataset dimensions number providers. more precise than existing approaches approximate solution by combining results, between 3x 250x faster privacy-preserving alternatives based solely computation encryption. work demonstrates practical applicability datasets.

Language: Английский

---

General Bootstrapping Approach for RLWE-Based Homomorphic Encryption

IEEE Transactions on Computers, Journal Year: 2023, Volume and Issue: 73(1), P. 86 - 96

Published: Sept. 22, 2023

Homomorphic Encryption (HE) makes it possible to compute on encrypted data without decryption. In lattice-based HE, a ciphertext contains noise, which accumulates along with homomorphic computations. Bootstrapping refreshes the noise and is perform arbitrary-depth computations HE bootstrapping, we call Fully (FHE). this article, propose new general bootstrapping technique for RLWE-based schemes its practical instantiation FHE. It can be applied all three leveled FHE schemes: Brakerski-Gentry-Vaikuntanathan (BGV), Brakerski/Fan-Vercauteren (BFV), Cheon-Kim-Kim-Song (CKKS) minor deviations in algorithms. Our construction of extracts noiseless part input, scales it, finally removes it. contrast previous algorithms, proposed method consumes only 1–2 levels uses smaller parameters. For BGV BFV, our does not have any restrictions plaintext modulus unlike typical cases methods. The error introduced by approach CKKS comparable rescaling error, allowing us preserve large amount precision after bootstrapping.

Language: Английский

---

META-BTS

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, Journal Year: 2022, Volume and Issue: unknown

Published: Nov. 7, 2022

Bootstrapping, which enables the full homomorphic encryption scheme that can perform an infinite number of operations by restoring modulus ciphertext with a small modulus, is essential step in encryption. However, bootstrapping most time and memory consuming all operations. As we increase precision bootstrapping, large amount computational resources required. Specifically, for any previous bootstrap designs, limited rescaling precision.

Language: Английский

---