Publications

A selection of my academic publications in homomorphic encryption and privacy-preserving computation in general.

2024

Towards Practical Homomorphic Aggregation in Byzantine-Resilient Distributed Learning

Antoine Choffrut, Rachid Guerraoui, Rafael Pinot, Renaud Sirdey, John Stephan, Martin Zuber — Middleware 2024

BibTeX

@inproceedings{ChoffrutGPSSZ24,
  author    = {Antoine Choffrut and Rachid Guerraoui and Rafael Pinot and Renaud Sirdey and John Stephan and Martin Zuber},
  title     = {Towards Practical Homomorphic Aggregation in Byzantine-Resilient Distributed Learning},
  booktitle = {Proceedings of the 25th International Middleware Conference, {MIDDLEWARE} 2024},
  pages     = {431--444},
  publisher = {{ACM}},
  year      = {2024},
  doi       = {10.1145/3652892.3700783}
}

2023

ComBo: A Novel Functional Bootstrapping Method for Efficient Evaluation of Nonlinear Functions in the Encrypted Domain

Pierre-Emmanuel Clet, Aymen Boudguiga, Renaud Sirdey, Martin Zuber — AFRICACRYPT 2023

DOI

BibTeX

@inproceedings{CletBSZ23,
  author    = {Pierre-Emmanuel Clet and Aymen Boudguiga and Renaud Sirdey and Martin Zuber},
  title     = {ComBo: {A} Novel Functional Bootstrapping Method for Efficient Evaluation of Nonlinear Functions in the Encrypted Domain},
  booktitle = {Progress in Cryptology - {AFRICACRYPT} 2023},
  series    = {Lecture Notes in Computer Science},
  volume    = {14064},
  pages     = {317--343},
  publisher = {Springer},
  year      = {2023},
  doi       = {10.1007/978-3-031-37679-5_14}
}

A Probabilistic Design for Practical Homomorphic Majority Voting with Intrinsic Differential Privacy

Arnaud Grivet Sébert, Martin Zuber, Oana Stan, Renaud Sirdey, Cédric Gouy-Pailler — WAHC 2023

DOI

BibTeX

@inproceedings{SebertZSSG23,
  author    = {Arnaud Grivet S{\'e}bert and Martin Zuber and Oana Stan and Renaud Sirdey and C{\'e}dric Gouy-Pailler},
  title     = {A Probabilistic Design for Practical Homomorphic Majority Voting with Intrinsic Differential Privacy},
  booktitle = {Proceedings of the 11th Workshop on Encrypted Computing \& Applied Homomorphic Cryptography},
  pages     = {47--58},
  publisher = {{ACM}},
  year      = {2023},
  doi       = {10.1145/3605759.3625258}
}

When Approximate Design for Fast Homomorphic Computation Provides Differential Privacy Guarantees

Arnaud Grivet Sébert, Martin Zuber, Oana Stan, Renaud Sirdey, Cédric Gouy-Pailler — arXiv 2023

arXiv

BibTeX

@article{SebertZSSG23arxiv,
  author    = {Arnaud Grivet S{\'e}bert and Martin Zuber and Oana Stan and Renaud Sirdey and C{\'e}dric Gouy-Pailler},
  title     = {When approximate design for fast homomorphic computation provides differential privacy guarantees},
  journal   = {CoRR},
  volume    = {abs/2304.02959},
  year      = {2023},
  eprint    = {2304.02959},
  eprinttype = {arXiv}
}

Practical Multi-Key Homomorphic Encryption for More Flexible and Efficient Secure Federated Average Aggregation

Alberto Pedrouzo-Ulloa, Aymen Boudguiga, Olive Chakraborty, Renaud Sirdey, Oana Stan, Martin Zuber — IEEE CSR 2023

DOI | ePrint

BibTeX

@inproceedings{PedrouzoUlloaBCSSZ23,
  author    = {Alberto Pedrouzo-Ulloa and Aymen Boudguiga and Olive Chakraborty and Renaud Sirdey and Oana Stan and Martin Zuber},
  title     = {Practical Multi-Key Homomorphic Encryption for More Flexible and Efficient Secure Federated Average Aggregation},
  booktitle = {{IEEE} International Conference on Cyber Security and Resilience, {CSR} 2023},
  pages     = {612--617},
  publisher = {{IEEE}},
  year      = {2023},
  doi       = {10.1109/CSR57506.2023.10224979}
}

A Practical and Scalable Privacy-preserving Framework

Nikos Avgerinos, Salvatore D’Antonio, Irene Kamara, Christos Kotselidis, Ioannis Lazarou, Teresa Mannarino, Georgios Meditskos, Konstantina Papachristopoulou, Angelos Papoutsis, Paolo Roccetti, Martin Zuber — IEEE CSR 2023

DOI

BibTeX

@inproceedings{AvgerinosDKKLMMPPRZ23,
  author    = {Nikos Avgerinos and Salvatore D'Antonio and Irene Kamara and Christos Kotselidis and Ioannis Lazarou and Teresa Mannarino and Georgios Meditskos and Konstantina Papachristopoulou and Angelos Papoutsis and Paolo Roccetti and Martin Zuber},
  title     = {A Practical and Scalable Privacy-preserving Framework},
  booktitle = {{IEEE} International Conference on Cyber Security and Resilience, {CSR} 2023},
  pages     = {598--603},
  publisher = {{IEEE}},
  year      = {2023},
  doi       = {10.1109/CSR57506.2023.10224928}
}

The Alliance of HE and TEE to Enhance their Performance and Security

Salvatore D’Antonio, Giannis Lazarou, Giovanni Mazzeo, Oana Stan, Martin Zuber, Ioannis Tsavdaridis — IEEE CSR 2023

DOI

BibTeX

@inproceedings{DAntonioLMSZT23,
  author    = {Salvatore D'Antonio and Giannis Lazarou and Giovanni Mazzeo and Oana Stan and Martin Zuber and Ioannis Tsavdaridis},
  title     = {The Alliance of {HE} and {TEE} to Enhance their Performance and Security},
  booktitle = {{IEEE} International Conference on Cyber Security and Resilience, {CSR} 2023},
  pages     = {641--647},
  publisher = {{IEEE}},
  year      = {2023},
  doi       = {10.1109/CSR57506.2023.10224999}
}

2022

Efficient and Accurate Homomorphic Comparisons

Olive Chakraborty, Martin Zuber — WAHC 2022

DOI | ePrint

BibTeX

@inproceedings{ChakrabortyZ22,
  author    = {Olive Chakraborty and Martin Zuber},
  title     = {Efficient and Accurate Homomorphic Comparisons},
  booktitle = {Proceedings of the 10th Workshop on Encrypted Computing \& Applied Homomorphic Cryptography},
  pages     = {35--46},
  publisher = {{ACM}},
  year      = {2022},
  doi       = {10.1145/3560827.3563375}
}

A Secure Federated Learning: Analysis of Different Cryptographic Tools

Oana Stan, Vincent Thouvenot, Aymen Boudguiga, Katarzyna Kapusta, Martin Zuber, Renaud Sirdey — SECRYPT 2022

DOI

BibTeX

@inproceedings{StanTBKZS22,
  author    = {Oana Stan and Vincent Thouvenot and Aymen Boudguiga and Katarzyna Kapusta and Martin Zuber and Renaud Sirdey},
  title     = {A Secure Federated Learning: Analysis of Different Cryptographic Tools},
  booktitle = {Proceedings of the 19th International Conference on Security and Cryptography, {SECRYPT} 2022},
  pages     = {669--674},
  publisher = {{SCITEPRESS}},
  year      = {2022},
  doi       = {10.5220/0011322700003283}
}

Putting Up the Swiss Army Knife of Homomorphic Calculations by Means of TFHE Functional Bootstrapping

Pierre-Emmanuel Clet, Martin Zuber, Aymen Boudguiga, Renaud Sirdey, Cédric Gouy-Pailler — IACR ePrint 2022

ePrint

BibTeX

@article{CletZBSG22,
  author    = {Pierre-Emmanuel Clet and Martin Zuber and Aymen Boudguiga and Renaud Sirdey and C{\'e}dric Gouy-Pailler},
  title     = {Putting up the swiss army knife of homomorphic calculations by means of {TFHE} functional bootstrapping},
  journal   = {{IACR} Cryptol. ePrint Arch.},
  pages     = {149},
  year      = {2022},
  url       = {https://eprint.iacr.org/2022/149}
}

2021

SPEED: Secure, PrivatE, and Efficient Deep Learning

Arnaud Grivet Sébert, Rafael Pinot, Martin Zuber, Cédric Gouy-Pailler, Renaud Sirdey — Machine Learning, Volume 110, Issue 4, 2021

DOI | arXiv

BibTeX

@article{SebertPZGS21,
  author    = {Arnaud Grivet S{\'e}bert and Rafael Pinot and Martin Zuber and C{\'e}dric Gouy-Pailler and Renaud Sirdey},
  title     = {{SPEED:} secure, PrivatE, and efficient deep learning},
  journal   = {Machine Learning},
  volume    = {110},
  number    = {4},
  pages     = {675--694},
  year      = {2021},
  doi       = {10.1007/s10994-021-05970-3}
}

Efficient Homomorphic Evaluation of k-NN Classifiers

Martin Zuber, Renaud Sirdey — Proceedings on Privacy Enhancing Technologies (PoPETs), 2021

DOI

BibTeX

@article{ZuberS21,
  author    = {Martin Zuber and Renaud Sirdey},
  title     = {Efficient homomorphic evaluation of k-NN classifiers},
  journal   = {Proceedings on Privacy Enhancing Technologies},
  volume    = {2021},
  number    = {2},
  pages     = {111--129},
  year      = {2021},
  doi       = {10.2478/popets-2021-0020}
}

BFV, CKKS, TFHE: Which One is the Best for a Secure Neural Network Evaluation in the Cloud?

Pierre-Emmanuel Clet, Oana Stan, Martin Zuber — ACNS Workshops 2021

DOI

BibTeX

@inproceedings{CletSZ21,
  author    = {Pierre-Emmanuel Clet and Oana Stan and Martin Zuber},
  title     = {BFV, CKKS, {TFHE:} Which One is the Best for a Secure Neural Network Evaluation in the Cloud?},
  booktitle = {Applied Cryptography and Network Security Workshops - {ACNS} 2021},
  series    = {Lecture Notes in Computer Science},
  volume    = {12809},
  pages     = {279--300},
  publisher = {Springer},
  year      = {2021},
  doi       = {10.1007/978-3-030-81645-2_16}
}

2020

Towards Real-Time Hidden Speaker Recognition by Means of Fully Homomorphic Encryption

Martin Zuber, Sergiu Carpov, Renaud Sirdey — ICICS 2020

DOI | ePrint

BibTeX

@inproceedings{ZuberCS20,
  author    = {Martin Zuber and Sergiu Carpov and Renaud Sirdey},
  title     = {Towards Real-Time Hidden Speaker Recognition by Means of Fully Homomorphic Encryption},
  booktitle = {Information and Communications Security - 22nd International Conference, {ICICS} 2020},
  series    = {Lecture Notes in Computer Science},
  volume    = {12282},
  pages     = {403--421},
  publisher = {Springer},
  year      = {2020},
  doi       = {10.1007/978-3-030-61078-4_23}
}

2019

Practical Fully Homomorphic Encryption for Fully Masked Neural Networks

Malika Izabachène, Renaud Sirdey, Martin Zuber — CANS 2019

DOI

BibTeX

@inproceedings{IzabacheneSZ19,
  author    = {Malika Izabach{\`e}ne and Renaud Sirdey and Martin Zuber},
  title     = {Practical Fully Homomorphic Encryption for Fully Masked Neural Networks},
  booktitle = {Cryptology and Network Security - 18th International Conference, {CANS} 2019},
  series    = {Lecture Notes in Computer Science},
  volume    = {11829},
  pages     = {24--36},
  publisher = {Springer},
  year      = {2019},
  doi       = {10.1007/978-3-030-31578-8_2}
}

Thesis

Contributions to Data Confidentiality in Machine Learning by Means of Homomorphic Encryption

Martin Zuber — PhD Thesis, Université Paris-Saclay, 2020

HAL

BibTeX

@phdthesis{Zuber20,
  author    = {Martin Zuber},
  title     = {Contributions to data confidentiality in machine learning by means of homomorphic encryption},
  school    = {Universit{\'e} Paris-Saclay},
  year      = {2020},
  url       = {https://hal.science/tel-03105524}
}