Byzantine machine learning: A primer

R Guerraoui, N Gupta, R Pinot - ACM Computing Surveys, 2024 - dl.acm.org
The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …

Private and reliable neural network inference

N Jovanovic, M Fischer, S Steffen… - Proceedings of the 2022 …, 2022 - dl.acm.org
Reliable neural networks (NNs) provide important inference-time reliability guarantees such
as fairness and robustness. Complementarily, privacy-preserving NN inference protects the …

Putting up the swiss army knife of homomorphic calculations by means of TFHE functional bootstrapping

PE Clet, M Zuber, A Boudguiga, R Sirdey… - Cryptology ePrint …, 2022 - eprint.iacr.org
In this work, we first propose a new functional bootstrapping with TFHE for evaluating any
function of domain and codomain the real torus T by using a small number of …

A comprehensive survey and taxonomy on privacy-preserving deep learning

AT Tran, TD Luong, VN Huynh - Neurocomputing, 2024 - Elsevier
Deep learning (DL) has been shown to be very effective for many application domains of
machine learning (ML), including image classification, voice recognition, natural language …

Combo: A novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain

PE Clet, A Boudguiga, R Sirdey, M Zuber - International Conference on …, 2023 - Springer
Abstract The application of Fully Homomorphic Encryption (FHE) to privacy issues arising in
inference or training of neural networks has been actively researched over the last few …

A probabilistic design for practical homomorphic majority voting with intrinsic differential privacy

A Grivet Sébert, M Zuber, O Stan, R Sirdey… - Proceedings of the 11th …, 2023 - dl.acm.org
As machine learning (ML) has become pervasive throughout various fields (industry,
healthcare, social networks), privacy concerns regarding the data used for its training have …

Practical homomorphic aggregation for byzantine ml

A Choffrut, R Guerraoui, R Pinot, R Sirdey… - arXiv preprint arXiv …, 2023 - arxiv.org
Due to the large-scale availability of data, machine learning (ML) algorithms are being
deployed in distributed topologies, where different nodes collaborate to train ML models …

Combining homomorphic encryption and differential privacy in federated learning

AG Sébert, M Checri, O Stan, R Sirdey… - 2023 20th Annual …, 2023 - ieeexplore.ieee.org
Recent works have investigated the relevance and practicality of using techniques such as
Differential Privacy (DP) or Homomorphic Encryption (HE) to strengthen training data privacy …

Efficient and accurate homomorphic comparisons

O Chakraborty, M Zuber - Proceedings of the 10th Workshop on …, 2022 - dl.acm.org
We design and implement a new efficient and accurate fully homomorphic argmin/min or
argmax/max comparison operator, which finds its application in numerous real-world use …

Privacy-Enhanced Knowledge Transfer with Collaborative Split Learning over Teacher Ensembles

Z Liu, J Guo, M Yang, W Yang, J Fan… - Proceedings of the 2023 …, 2023 - dl.acm.org
Knowledge Transfer has received much attention for its ability to transfer knowledge, rather
than data, from one application task to another. In order to comply with the stringent data …