Jean-Philippe Bossuat

Jean-Philippe Bossuat

Auto-generated profile, based on publicly available information

Jean-Philippe Bossuat

Independent

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2025 in IACR Communications in Cryptology
Verified
Journal Article
Open access
PDF file
JBJean-Philippe Bossuat
Jean-Philippe Bossuat
RCRosario Cammarota
Rosario Cammarota
ICIlaria Chillotti
Ilaria Chillotti
BCBenjamin R. Curtis
Benjamin R. Curtis
WDWei Dai
Wei Dai
DYDonggeon Yhee
Donggeon Yhee
Fully Homomorphic Encryption (FHE) is a cryptographic primitive that allows performing arbitrary operations on encrypted data. Since the conception of the idea in [RAD78], it has been considered a holy grail of cryptography. After the first construction in 2009 [Gen09], it has evolved to become a practical primitive with strong security guarantees. Most modern constructions are based on well-known lattice problems such as Learning With Errors (LWE). Besides its academic appeal, in recent years FHE has also attracted significant attention from industry, thanks to its applicability to a considerable number of real-world use-cases. An upcoming standardization effort by ISO/IEC aims to support the wider adoption of these techniques. However, one of the main challenges that standards bodies, developers, and end users usually encounter is establishing parameters. This is particularly hard in the case of FHE because the parameters are not only related to the security level of the system, but also to the type of operations that the system is able to handle. In this paper we provide examples of parameter sets for LWE targeting particular security levels, that can be used in the context of FHE constructions. We also give examples of complete FHE parameter sets, including the parameters relevant for correctness and performance, alongside those relevant for security. As an additional contribution, we survey the parameter selection support offered in open-source FHE libraries.

7 July 2025 in IACR Communications in Cryptology
Verified
Journal Article
Open access
PDF file
JBJean-Philippe Bossuat
Jean-Philippe Bossuat
ACAnamaria Costache
Anamaria Costache
CMChristian Mouchet
Christian Mouchet
LNLea Nürnberger
Lea Nürnberger
JTJuan Ramón Troncoso-Pastoriza
Juan Ramón Troncoso-Pastoriza
All RLWE-based FHE schemes are inherently noisy. The CKKS scheme (Cheon, Kim, Kim, Song, Asiacrypt 2017) considers the noise as a part of the message, yielding approximate computations but also considerable performance gains. Since it grows with each homomorphic operation and incurs a precision loss, it is paramount for users to be able to estimate the noise level throughout a given circuit in order to appropriately estimate parameters and control the precision loss in the message. In this work, we develop a noise model that allows for tight estimates of the precision loss, and propose a tool prototype for computing these estimates on any given circuit. Our noise model relies on a novel definition, the component-wise noise, which makes the average-case noise estimates tighter and more composable. As a result, our model and tool can derive accurate estimates of complex circuits such as bootstrapping. We experimentally demonstrate the tightness of our noise estimates by showing that our theoretical estimates never deviate by more than 0.01 bits from experimental estimates, even for large circuits, and hold with high probability. Furthermore, we demonstrate how to apply our techniques to obtain an exact version of the CKKS scheme in which the decryption removes all the noise (with high probability). Such a scheme has many applications, as it allows to take advantage of the efficiency of CKKS, while preserving an exact message space, hence further strengthening CKKS against IND-CPA-D attacks.

11 January 2022 in bioRxiv
Verified
Preprint
Open access
PDF file
SSSinem Sav
Sinem Sav
JBJean-Philippe Bossuat
Jean-Philippe Bossuat
JTJuan R. Troncoso-Pastoriza
Juan R. Troncoso-Pastoriza
MCManfred Claassen
Manfred Claassen
JHJean-Pierre Hubaux
Jean-Pierre Hubaux
Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data-silos. Sharing or centralizing the data of different healthcare institutions is, however, unfeasible or prohibitively difficult due to privacy regulations. In this work, we address this problem by using a novel privacy-preserving federated learning-based approach, PriCell , for complex machine learning models such as convolutional neural networks. PriCell relies on multiparty homomorphic encryption and enables the collaborative training of encrypted neural networks with multiple healthcare institutions. We preserve the confidentiality of each institutions’ input data, of any intermediate values, and of the trained model parameters. We efficiently replicate the training of a published state-of-the-art convolutional neural network architecture in a decentralized and privacy-preserving manner. Our solution achieves an accuracy comparable to the one obtained with the centralized solution, with an improvement of at least one-order-of-magnitude in execution time with respect to prior secure solutions. Our work guarantees patient privacy and ensures data utility for efficient multi-center studies involving complex healthcare data.

1 April 2025 in Proceedings on Privacy Enhancing Technologies
Verified
Journal Article
Open access
PDF file
MIMalika Izabachène
Malika Izabachène
JBJean-Philippe Bossuat
Jean-Philippe Bossuat
To derive valuable insights from statistics, machine learning applications frequently analyze substantial amounts of data. In this work, we address the problem of designing efficient secure techniques to probe large datasets which allow a scientist to conduct large-scale medical studies over specific attributes of patients' records, while maintaining the privacy of his model. We introduce a set of composable homomorphic operations and show how to combine private functions evaluation with private thresholds via approximate fully homomorphic encryption. This allows us to design a new system named TETRIS, which solves the real-world use case of private functional exploration of large databases, where the statistical criteria remain private to the server owning the patients’ records. Our experiments show that TETRIS achieves practical performance over a large dataset of patients even for the evaluation of elaborate statements composed of linear and nonlinear functions. It is possible to extract private insights from a database of hundreds of thousands of patient records within only a few minutes on a single thread, with an amortized time per database entry smaller than 2ms.

3 May 2023 in arXiv
Verified
Preprint
Open access
PDF file
SSSinem Sav
Sinem Sav
ADAbdulrahman Diaa
Abdulrahman Diaa
APApostolos Pyrgelis
Apostolos Pyrgelis
JBJean-Philippe Bossuat
Jean-Philippe Bossuat
JHJean-Pierre Hubaux
Jean-Pierre Hubaux
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the confidentiality of the training data, the model, and the prediction data; and it mitigates federated learning attacks that target the gradients under a passive-adversary threat model. We propose a packing scheme, multi-dimensional packing, for a better utilization of Single Instruction, Multiple Data (SIMD) operations under encryption. With multi-dimensional packing, RHODE enables the efficient processing, in parallel, of a batch of samples. To avoid the exploding gradients problem, RHODE provides several clipping approximations for performing gradient clipping under encryption. We experimentally show that the model performance with RHODE remains similar to non-secure solutions both for homogeneous and heterogeneous data distribution among the data holders. Our experimental evaluation shows that RHODE scales linearly with the number of data holders and the number of timesteps, sub-linearly and sub-quadratically with the number of features and the number of hidden units of RNNs, respectively. To the best of our knowledge, RHODE is the first system that provides the building blocks for the training of RNNs and its variants, under encryption in a federated learning setting.

17 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
MIMalika Izabachène
Malika Izabachène
JBJean-Philippe Bossuat
Jean-Philippe Bossuat
To derive valuable insights from statistics, machine learning applications frequently analyze substantial amounts of data. In this work, we address the problem of designing efficient secure techniques to probe large datasets which allow a scientist to conduct large-scale medical studies over specific attributes of patients' records, while maintaining the privacy of his model. We introduce a set of composable homomorphic operations and show how to combine private functions evaluation with private thresholds via approximate fully homomorphic encryption. This allows us to design a new system named TETRIS, which solves the real-world use case of private functional exploration of large databases, where the statistical criteria remain private to the server owning the patients' records. Our experiments show that TETRIS achieves practical performance over a large dataset of patients even for the evaluation of elaborate statements composed of linear and nonlinear functions. It is possible to extract private insights from a database of hundreds of thousands of patient records within only a few minutes on a single thread, with an amortized time per database entry smaller than 2ms.