Practical Fully Homomorphic Encryption for Fully Masked Neural Networks

Izabachène, Malika; Sirdey, Renaud; Zuber, Martin

doi:10.1007/978-3-030-31578-8_2

Cited by 15 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can evaluate some other functions by just adjusting the value of µ. For example, the sign function, as used in FHE-DiNN [BMMP18] and by Izabachène et al [ISZ19]. To evaluate an arbitrary LUT (with more than one value and its negative), we need to increase the size of the LUT, to discretize the function according to this size, and to work only with the positive half of the Torus, since the negacyclic property can only be explored by anti-symmetric functions.…”

Section: Functional Bootstrap In Tfhementioning

confidence: 99%

“…For example, with B = 4, the size of each Torus slice is 0.125 and the map of integers is (0, 1, 2, 3) → (0, 0.125, 0.25, 0.375). This approach has been extensively used to represent bounded integers in the Torus [BMMP18,CIM19,ISZ19]. To represent unbounded integers, we decompose them in digits of the base B and encrypt each digit in a TLWE sample.…”

Section: Functional Bootstrap In Tfhementioning

confidence: 99%

“…Evaluation of neural network inference using the Functional Bootstrap Using the functional bootstrap of TFHE in neural network inference seems to be a recent (and promising) trend. As previously cited, FHE-DiNN [BMMP18] and Izabachène et al [ISZ19] implemented the sign activation function using it. Boura et al [BGGJ19] simulated the error propagation of several activation functions and introduced the term Functional bootstrap, which we adopt in this paper.…”

Section: Related Workmentioning

confidence: 99%

“…This idea was introduced with the FHEW cryptosystem [DM15,MP20] and has been used by a few applications in the literature. We can refer, for example, to FHE-DiNN [BMMP18] and the work of Izabachène et al [ISZ19], which both implement the sign function using the functional bootstrap of the TFHE cryptosystem [CGGI20]. These applications can perform a functional bootstrap in just tens of milliseconds thanks to the low precision (1 bit) required by the sign function.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Revisiting the functional bootstrap in TFHE

Guimarães

Borin

Aranha

2021

TCHES

View full text Add to dashboard Cite

The FHEW cryptosystem introduced the idea that an arbitrary function can be evaluated within the bootstrap procedure as a table lookup. The faster bootstraps of TFHE strengthened this approach, which was later named Functional Bootstrap (Boura et al., CSCML’19). From then on, little effort has been made towards defining efficient ways of using it to implement functions with high precision. In this paper, we introduce two methods to combine multiple functional bootstraps to accelerate the evaluation of reasonably large look-up tables and highly precise functions. We thoroughly analyze and experimentally validate the error propagation in both methods, as well as in the functional bootstrap itself. We leverage the multi-value bootstrap of Carpov et al. (CT-RSA’19) to accelerate (single) lookup table evaluation, and we improve it by lowering the complexity of its error variance growth from quadratic to linear in the value of the output base. Compared to previous literature using TFHE’s functional bootstrap, our methods are up to 2.49 times faster than the lookup table evaluation of Carpov et al. (CT-RSA’19) and up to 3.19 times faster than the 32-bit integer comparison of Bourse et al. (CT-RSA’20). Compared to works using logic gates, we achieved speedups of up to 6.98, 8.74, and 3.55 times over 8-bit implementations of the functions ReLU, Addition, and Maximum, respectively.

show abstract

Section: Functional Bootstrap In Tfhementioning

confidence: 99%

Section: Functional Bootstrap In Tfhementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Revisiting the functional bootstrap in TFHE

Guimarães

Borin

Aranha

2021

TCHES

View full text Add to dashboard Cite

show abstract

“…On the other hand, any datadriving mechanism heavily relies on the quantity and quality of information, which brings about the conflict between data usability and data confidentiality. Fortunately, secure multiparty computation (SMC) [5][6][7] and homomorphic encryption (HE) [8,9] provide us powerful tools to process data in a concealed manner.…”

Section: Introductionmentioning

confidence: 99%

Multiparty Homomorphic Machine Learning with Data Security and Model Preservation

Kuang

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the widespread application of machine learning (ML), data security has been a serious issue. To eliminate the conflict between data privacy and computability, homomorphism is extensively researched due to its capacity of performing operations over ciphertexts. Considering that the data provided by a single party are not always adequate to derive a competent model via machine learning, we proposed a privacy-preserving training method for the neural network over multiple data providers. Moreover, taking the trainer’s intellectual property into account, our scheme also achieved the goal of model parameter protection. Thanks to the hardness of the conjugate search problem (CSP) and discrete logarithm problem (DLP), the confidentiality of training data and system model can be reduced to well-studied security assumptions. In terms of efficiency, since all messages are coded as low-dimensional matrices, the expansion rates with regard to storage and computation overheads are linear compared to plaintext implementation without accuracy loss. In reality, our method can be transplanted to any machine learning system involving multiple parties due to its capacity of fully homomorphic computation.

show abstract