VLDB 2026 Research / reviewers in the wild / expert

Franck Leprévost

dblp:60/5914 · DBLP profile ↗
← Back
7ranked-venue papers
3as first author
4since 2021 · last 2026
0000-0001-8808-2730ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Databases, data management, data science and information retrieval · 6 · 3 first-author · 4 since 2021Artificial intelligence and machine learning · 5 · 2 first-author · 4 since 2021Theory of computation · 1 · 1 first-author
YearPublicationVenuePosition
2026 Speech-EA: Evolutionary Algorithm-Based Attack on Automatic Speech Recognition Systems
Elmir Avdusinovic, Ali Osman Topal, Enea Mançellari, Faraz Mohammad Mushtak Mogal, Franck Leprévost
 ACIIDS (2)6
2023 Creating High-Resolution Adversarial Images Against Convolutional Neural Networks with the Noise Blowing-Up Method
Franck Leprévost, Ali Osman Topal, Enea Mançellari
 ACIIDS (1)1
2023 Scheduling Deep Learning Training in GPU Cluster Using the Model-Similarity-Based Policy
Panissara Thanapol, Kittichai Lavangnananda, Franck Leprévost, Julien Schleich, Pascal Bouvry
 ACIIDS (2)3
2022 Strategy and Feasibility Study for the Construction of High Resolution Images Adversarial Against Convolutional Neural Networks
Franck Leprévost, Ali Osman Topal, Elmir Avdusinovic, Raluca Chitic
 ACIIDS (1)1
2020 A Proof of Concept to Deceive Humans and Machines at Image Classification with Evolutionary Algorithms
Raluca Chitic, Nicolas Bernard, Franck Leprévost
 ACIIDS (2)3
2005 Generating anomalous elliptic curves
Franck Leprévost, Jean Monnerat, Sébastien Varrette, Serge Vaudenay
 Inf. Process. Lett.1
2004 FlowCert : Probabilistic Certification for Peer-to-Peer Computations
abstract
Large scale cluster, peer-to-peer computing systems and grid computer systems gather thousands of nodes for computing parallel applications. At this scale, it raises the problem of the result checking of the parallel execution of a program on an unsecured grid. This domain is the object of numerous works, either at the hardware or at the software level. We propose here an original software method based on the dynamic computation of the data-flow associated to a partial execution of the program on a secure machine. This data-flow is a summary of the execution: any complete execution of the program on an unsecured remote machine with the same inputs supplies a flow which summary has to correspond to the one obtained by partial execution.
Sébastien Varrette, Jean-Louis Roch, Franck Leprévost
 SBAC-PAD3