An official website of the United States government
Homomorphic Encryption (HE) based secure Neural Networks(NNs) inference is one of the most promising security solutions to emerging Machine Learning as a Service (MLaaS). In the HE-based MLaaS setting, a client encrypts the sensitive data, and uploads the encrypted data to the server that directly processes the encrypted data without decryption, and returns the encrypted result to the client. The clients' data privacy is preserved since only the client has the private key. Existing HE-enabled Neural Networks (HENNs), however, suffer from heavy computational overheads. The state-of-the-art HENNs adopt ciphertext packing techniques to reduce homomorphic multiplications by packing multiple messages into one single ciphertext. Nevertheless, rotations are required in these HENNs to implement the sum of the elements within the same ciphertext. We observed that HENNs have to pay significant computing overhead on rotations, and each of rotations is ∼10× more expensive than homomorphic multiplications between ciphertext and plaintext. So the massive rotations have become a primary obstacle of efficient HENNs. In this paper, we propose a fast, frequency-domain deep neural network called Falcon, for fast inferences on encrypted data. Falcon includes a fast Homomorphic Discrete Fourier Transform (HDFT) using block-circulant matrices to homomorphically support spectral operations. We also propose several efficient methods to reduce inference latency, including Homomorphic Spectral Convolution and Homomorphic Spectral Fully Connected operations by combing the batched HE and block-circulant matrices. Our experimental results show Falcon achieves the state-of-the-art inference accuracy and reduces the inference latency by 45.45%∼85.34% over prior HENNs on MNIST and CIFAR-10.
more »
« less
Juliet: A Configurable Processor for Computing on Encrypted Data
Fully homomorphic encryption (FHE) has become progressively more viable in the years since its original inception in 2009. At the same time, leveraging state-of-the-art schemes in an efficient way for general computation remains prohibitively difficult for the average programmer. In this work, we introduce a new design for a fully homomorphic processor, dubbed Juliet, to enable faster operations on encrypted data using the state-of-the-art TFHE and cuFHE libraries for both CPU and GPU evaluation. To improve usability, we define an expressive assembly language and instruction set architecture (ISA) judiciously designed for end-to-end encrypted computation. We demonstrate Juliet’s capabilities with a broad range of realistic benchmarks including cryptographic algorithms, such as the lightweight ciphers SIMON and SPECK, as well as logistic regression (LR) inference and matrix multiplication.
more »
« less
- Award ID(s):
- 2239334
- PAR ID:
- 10518989
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Transactions on Computers
- ISSN:
- 0018-9340
- Page Range / eLocation ID:
- 1-14
- Subject(s) / Keyword(s):
- Applied Cryptography Encrypted Processor Hardware Acceleration Homomorphic Encryption Privacy-Enhancing Technologies Privacy-Preserving ISA Private Computation Secure Cloud Computing
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Because of the lack of expertise, to gain benefits from their data, average users have to upload their private data to cloud servers they may not trust. Due to legal or privacy constraints, most users are willing to contribute only their encrypted data, and lack interests or resources to join deep neural network (DNN) training in cloud. To train a DNN on encrypted data in a completely non-interactive way, a recent work proposes a fully homomorphic encryption (FHE)-based technique implementing all activations by \textit{Brakerski-Gentry-Vaikuntanathan} (BGV)-based lookup tables. However, such inefficient lookup-table-based activations significantly prolong private training latency of DNNs. In this paper, we propose, Glyph, an FHE-based technique to fast and accurately train DNNs on encrypted data by switching between TFHE (Fast Fully Homomorphic Encryption over the Torus) and BGV cryptosystems. Glyph uses logic-operation-friendly TFHE to implement nonlinear activations, while adopts vectorial-arithmetic-friendly BGV to perform multiply-accumulations (MACs). Glyph further applies transfer learning on DNN training to improve test accuracy and reduce the number of MACs between ciphertext and ciphertext in convolutional layers. Our experimental results show Glyph obtains state-of-the-art accuracy, and reduces training latency by 69%~99% over prior FHE-based privacy-preserving techniques on encrypted datasets.more » « less
-
null (Ed.)As the demand for machine learning–based inference increases in tandem with concerns about privacy, there is a growing recognition of the need for secure machine learning, in which secret models can be used to classify private data without the model or data being leaked. Fully Homomorphic Encryption (FHE) allows arbitrary computation to be done over encrypted data, providing an attractive approach to providing such secure inference. While such computation is often orders of magnitude slower than its plaintext counterpart, the ability of FHE cryptosystems to do ciphertext packing—that is, encrypting an entire vector of plaintexts such that operations are evaluated elementwise on the vector—helps ameliorate this overhead, effectively creating a SIMD architecture where computation can be vectorized for more efficient evaluation. Most recent research in this area has targeted regular, easily vectorizable neural network models. Applying similar techniques to irregular ML models such as decision forests remains unexplored, due to their complex, hard-to-vectorize structures. In this paper we present COPSE, the first system that exploits ciphertext packing to perform decision-forest inference. COPSE consists of a staging compiler that automatically restructures and compiles decision forest models down to a new set of vectorizable primitives for secure inference. We find that COPSE’s compiled models outperform the state of the art across a range of decision forest models, often by more than an order of magnitude, while still scaling well.more » « less
-
Fully Homomorphic Encryption (FHE) enables computing on encrypted data, letting clients securely offload computation to untrusted servers. While enticing, FHE has two key challenges that limit its applicability: it has high performance overheads (10,000× over unencrypted computation) and it is extremely hard to program. Recent hardware accelerators and algorithmic improvements have reduced FHE’s overheads and enabled large applications to run under FHE. These large applications exacerbate FHE’s programmability challenges. Writing FHE programs directly is hard because FHE schemes expose a restrictive, low-level interface that prevents abstraction and composition. Specifically, FHE requires packing encrypted data into large vectors (tens of thousands of elements long), FHE provides limited operations on these vectors, and values have noise that grows with each operation, which creates unintuitive performance tradeoffs. As a result, translating large applications, like neural networks, into efficient FHE circuits takes substantial tedious work. We address FHE’s programmability challenges with the Fhelipe FHE compiler. Fhelipe exposes a simple, numpy-styletensorprogramming interface, and compiles high-level tensor programs into efficient FHE circuits. Fhelipe’s key contribution isautomatic data packing, which chooses data layouts for tensors and packs them into ciphertexts to maximize performance. Our novel framework considers a wide range of layouts and optimizes them analytically. This lets compile large FHE programs efficiently, unlike prior FHE compilers, which either use inefficient layouts or do not scale beyond tiny programs. We evaluate on both a state-of-the-art FHE accelerator and a CPU. is the first compiler that matches or exceeds the performance of large hand-optimized FHE applications, like deep neural networks, and outperforms a state-of-the-art FHE compiler by gmean 18.5. At the same time, dramatically simplifies programming, reducing code size by 10–48.more » « less
-
Dynamic Searchable Symmetric Encryption (DSSE) allows to delegate keyword search and file update over an encrypted database via encrypted indexes, and therefore provides opportunities to mitigate the data privacy and utilization dilemma in cloud storage platforms. Despite its merits, recent works have shown that efficient DSSE schemes are vulnerable to statistical attacks due to the lack of forward-privacy, whereas forward-private DSSE schemes suffers from practicality concerns as a result of their extreme computation overhead. Due to significant practical impacts of statistical attacks, there is a critical need for new DSSE schemes that can achieve the forward-privacy in a more practical and efficient manner. We propose a new DSSE scheme that we refer to as Forward-private Sublinear DSSE (FS-DSSE). FS-DSSE harnesses special secure update strategies and a novel caching strategy to reduce the computation cost of repeated queries. Therefore, it achieves forward-privacy, sublinear search complexity, low end-to-end delay, and parallelization capability simultaneously. We fully implemented our proposed method and evaluated its performance on a real cloud platform. Our experimental evaluation results showed that the proposed scheme is highly secure and highly efficient compared with state-of-the-art DSSE techniques. Specifically, FS-DSSE is up to three magnitude of times faster than forward-secure DSSE counterparts, depending on the frequency of the searched keyword in the database.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TC.2024.3416752
