WTFHE: neural-netWork-ready Torus Fully Homomorphic Encryption

Klemsa, Jakub; Novotný, Martin

doi:10.1109/meco49872.2020.9134331

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [7,19], authors suggest to employ only one half of the plaintext space, which is the generic approach. On the other hand, Klemsa et al [22] suggest to exploit any possible overlap of the negacyclic extension (cf. Figure 3 in their paper), which may lead to plaintext space savings.…”

Section: Minimizing the Plaintext Spacementioning

confidence: 99%

Parallel Operations over TFHE-Encrypted Multi-Digit Integers

Klemsa

Önen

2022

Proceedings of the Twelfth ACM Conference on Data and Application Security and Privacy

Self Cite

View full text Add to dashboard Cite

Recent advances in Fully Homomorphic Encryption (FHE) allow for a practical evaluation of non-trivial functions over encrypted data. In particular, novel approaches for combining ciphertexts broadened the scope of prospective applications. However, for arithmetic circuits, the overall complexity grows with the desired precision and there is only a limited space for parallelization.In this paper, we put forward several methods for fully parallel addition of multi-digit integers encrypted with the TFHE scheme. Since these methods handle integers in a special representation, we also revisit the signum function, firstly addressed by Bourse et al., and we propose a method for the maximum of two numbers; both with particular respect to parallelization. On top of that, we outline an approach for multiplication by a known integer.According to our experiments, the fastest approach for parallel addition of 31-bit encrypted integers in an idealized setting with 32 threads is estimated to be more than 6× faster than the fastest sequential approach. Finally, we demonstrate our algorithms on an evaluation of a practical neural network.

show abstract

Section: Minimizing the Plaintext Spacementioning

confidence: 99%

Parallel Operations over TFHE-Encrypted Multi-Digit Integers

Klemsa

Önen

2022

Proceedings of the Twelfth ACM Conference on Data and Application Security and Privacy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Boura et al [BGGJ19] simulated the error propagation of several activation functions and introduced the term Functional bootstrap, which we adopt in this paper. Klemsa et al [KN20] presented a Ruby version of TFHE, which includes the functional bootstrap, targeted at neural network implementations. From all previous literature, the only one we found to combine multiple functional bootstraps to evaluate a single function is the integer comparison of Bourse et al [BST20].…”

Section: Related Workmentioning

confidence: 99%

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

TFHE Parameter Setup for Effective and Error-Free Neural Network Prediction on Encrypted Data

Klemsa

2021

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

WTFHE: neural-netWork-ready Torus Fully Homomorphic Encryption

Cited by 3 publications

References 15 publications

Parallel Operations over TFHE-Encrypted Multi-Digit Integers

Parallel Operations over TFHE-Encrypted Multi-Digit Integers

Revisiting the functional bootstrap in TFHE

TFHE Parameter Setup for Effective and Error-Free Neural Network Prediction on Encrypted Data

Contact Info

Product

Resources

About