From the 1 of 20 papers with an AI index.
9 citations
- Télécom ParisFR4 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- École Normale Supérieure de LyonFR3 papers
- Lyon 1 UniversitéFR2 papers
- CentraleSupélecFR1 paper
- Centre Inria de SaclayFR1 paper
- Consejo Superior de Investigaciones CientíficasES1 paper
- CryptoExperts (France)FR1 paper
- Delft University of TechnologyNL1 paper
- Deutsch Amerikanisches Institut SaarlandDE1 paper
- École Centrale de LilleFR1 paper
- École PolytechniqueFR1 paper
20 papers
CutClean: Neural Network Pruning for Privacy-Preserving Inference
Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise +1
Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of repr…
Not In My Git Yard: Catching Backdoors at Commit and Release Time
Dimitri Kokkonis, Michaël Marcozzi, Stefano Zacchiroli
The paper introduces Lily, a tool that automatically detects hidden backdoors in open‑source code during commit and release stages by combining CI‑compatible fuzzing with code‑chan…
Two Means to an End Goal: Connecting Explainability and Contestability in the Regulation of Public Sector AI
Timothée Schmude, Mireia Yurrita, Kars Alfrink +3
Explainability and its emerging counterpart contestability have become important normative and design principles for trustworthy AI as they enable users and subjects to understand…
Understanding Build Reproducibility in the F-Droid Ecosystem
Denise Nanni, Julien Malka, Stefano Zacchiroli +2
The security of open source applications benefits considerably from the possibility of rebuilding their source and verifying the output. F-Droid, a prominent distribution for open…
Mutating the "Immutable": A Large-Scale Study of Git Tag Alterations
Solal Rapaport, Laurent Pautet, Samuel Tardieu +2
Git tags are commonly viewed as immutable references in software development, marking releases and specific repository states that underpin build reproducibility and software suppl…
AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors
Maher Boughdiri, Mounira Msahli, Albert Bifet
Deep neural networks (DNNs) have shown outstanding performance in visual recognition tasks within vision sensor networks; however, they are still vulnerable to adversarial manipula…