Computing Neural Networks with Homomorphic Encryption and Verifiable Computing

Madi, Abbass; Sirdey, Renaud; Stan, Oana

doi:10.1007/978-3-030-61638-0_17

Cited by 8 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, one key contribution of [30] was to associate Paillierbased homomorphic calculations to Verifiable Computing (VC) techniques (e.g. [14]) to further extend the server threat model beyond the honest-but-curious one and bring execution integrity, as [29] did with BFV scheme. However, these works lacked DP.…”

Section: Homomorphic Encryption Protects the Data (And The Model) Aga...mentioning

confidence: 99%

Protecting Data from all Parties: Combining FHE and DP in Federated Learning

Sébert¹,

Sirdey²,

Stan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper tackles the problem of ensuring training data privacy in a federated learning context. Relying on Homomorphic Encryption (HE) and Differential Privacy (DP), we propose a framework addressing threats on the privacy of the training data. Notably, the proposed framework ensures the privacy of the training data from all actors of the learning process, namely the data owners and the aggregating server. More precisely, while HE blinds a semi-honest server during the learning protocol, DP protects the data from semi-honest clients participating in the training process as well as end-users with black-box or white-box access to the trained model. In order to achieve this, we provide new theoretical and practical results to allow these techniques to be rigorously combined. In particular, by means of a novel stochastic quantisation operator, we prove DP guarantees in a context where the noise is quantised and bounded due to the use of HE. The paper is concluded by experiments which show the practicality of the entire framework in terms of both model quality (impacted by DP) and computational overhead (impacted by HE).

show abstract

Section: Homomorphic Encryption Protects the Data (And The Model) Aga...mentioning

confidence: 99%

Protecting Data from all Parties: Combining FHE and DP in Federated Learning

Sébert¹,

Sirdey²,

Stan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…4) Machine-Learning Prediction: Advances in machine learning (ML) enable new ways for data analytics and several works explore the use of HE in order to protect, during ML inference, data confidentiality [24], [97], [108], [137], [141]. However, as the correctness of the prediction can be tantamount to confidentiality, we apply VERITAS to an encrypted ML inference pipeline.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…However, as the correctness of the prediction can be tantamount to confidentiality, we apply VERITAS to an encrypted ML inference pipeline. Indeed, misclassification or malicious predictions could render the application pointless and have dire consequences, such as financial misprediction or cyberthreat misclassification, for the end users [63], [135], [97], [137].…”

Section: Experimental Evaluationmentioning

confidence: 99%

Verifiable Encodings for Secure Homomorphic Analytics

Chatel¹,

Knabenhans²,

Pyrgelis³

et al. 2022

Preprint

View full text Add to dashboard Cite

Homomorphic encryption, which enables the execution of arithmetic operations directly on ciphertexts, is a promising solution for protecting privacy of cloud-delegated computations on sensitive data. However, the correctness of the computation result is not ensured. We propose two error detection encodings and build authenticators that enable practical client-verification of cloud-based homomorphic computations under different trade-offs and without compromising on the features of the encryption algorithm. Our authenticators operate on top of trending ring learning with errors based fully homomorphic encryption schemes over the integers. We implement our solution in VERITAS, a ready-to-use system for verification of outsourced computations executed over encrypted data. We show that contrary to prior work VERITAS supports verification of any homomorphic operation and we demonstrate its practicality for various applications, such as ride-hailing, genomic-data analysis, encrypted search, and machine-learning training and inference.

show abstract

“…Not at all. Indeed, with respect to Convolutional Neural Networks (CNN), starting with the work of Dowlin et al on CryptoNets [14], several works have investigated the application of various flavors of homomorphic encryption techniques to various flavors of neural networks with the long-term goal of achieving the above setup [7,6,21,2,19,24,1,10]. However, these works have so far achieved limited scaling (reaching throughputs ranging from a few hundred to a few thousand neurons per minute) and had to resort to simple activation functions (for instance square, Sign, or ReLU).…”

Section: Introductionmentioning

confidence: 99%

Building Blocks for LSTM Homomorphic Evaluation with TFHE

Trama,

Clet,

Boudguiga

et al. 2023

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Long Short-Term Memory (LSTM) is a Neural Network (NN) type that creates temporal connections between its nodes. It models sequence data for applications such as speech recognition, image captioning, DNA sequence analysis, and sentence translation. Applications that are often subject to privacy constraints. This paper thus presents basic building blocks for the homomorphic execution of an LSTM that would respect the privacy of its inputs. By means of TFHE functional bootstrapping, we propose several approaches for homomorphically evaluating discretized flavors of the Sigmoid and Tanh activation functions. Experimental results show that the accuracy of the resulting discretized networks remains comparable to a full precision clear-domain execution. Performance-wise, we are able to homomorphically compute a Sigmoid or Tanh function in 0.3 or 0.15 secs (depending on whether or not multivalue bootstrapping is relied on). This paves the way towards evaluating practical LSTMs over encrypted inputs in around 1 to 3 mins which is competitive with the state of the art.

show abstract

Computing Neural Networks with Homomorphic Encryption and Verifiable Computing

Cited by 8 publications

References 16 publications

Protecting Data from all Parties: Combining FHE and DP in Federated Learning

Protecting Data from all Parties: Combining FHE and DP in Federated Learning

Verifiable Encodings for Secure Homomorphic Analytics

Building Blocks for LSTM Homomorphic Evaluation with TFHE

Contact Info

Product

Resources

About