18 citations · 34 across the 8 of their papers we have counts for
9 papers
Robust Federated Learning via Byzantine Filtering over Encrypted Updates
Adda Akram Bendoukha, Aymen Boudguiga, Nesrine Kaaniche +3
Federated Learning (FL) aims to train a collaborative model while preserving data privacy. However, the distributed nature of this approach still raises privacy and security issues…
SABLE: Secure And Byzantine robust LEarning
Antoine Choffrut, Rachid Guerraoui, Rafael Pinot +3
Due to the widespread availability of data, machine learning (ML) algorithms are increasingly being implemented in distributed topologies, wherein various nodes collaborate to trai…
When approximate design for fast homomorphic computation provides differential privacy guarantees
Arnaud Grivet Sébert, Martin Zuber, Oana Stan +2
While machine learning has become pervasive in as diversified fields as industry, healthcare, social networks, privacy concerns regarding the training data have gained a critical i…
Homomorphic Sortition -- Secret Leader Election for PoS Blockchains
Luciano Freitas, Andrei Tonkikh, Adda-Akram Bendoukha +4
In a single secret leader election protocol (SSLE), one of the system participants is chosen and, unless it decides to reveal itself, no other participant can identify it. SSLE has…
Protecting Data from all Parties: Combining FHE and DP in Federated Learning
Arnaud Grivet Sébert, Renaud Sirdey, Oana Stan +1
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…
RandSolomon: Optimally Resilient Random Number Generator with Deterministic Termination
Luciano Freitas de Souza, Andrei Tonkikh, Sara Tucci-Piergiovanni +4
Multi-party random number generation is a key building-block in many practical protocols. While straightforward to solve when all parties are trusted to behave correctly, the probl…
SPEED: Secure, PrivatE, and Efficient Deep learning
Arnaud Grivet Sébert, Rafael Pinot, Martin Zuber +2
We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed…
Revisiting old combinatorial beasts in the quantum age: quantum annealing versus maximal matching
Daniel Vert, Renaud Sirdey, Stéphane Louise
This paper experimentally investigates the behavior of analog quantum computers such as commercialized by D-Wave when confronted to instances of the maximum cardinality matching pr…
A linear programming approach to general dataflow process network verification and dimensioning
Renaud Sirdey, Pascal Aubry
In this paper, we present linear programming-based sufficient conditions, some of them polynomial-time, to establish the liveness and memory boundedness of general dataflow process…