2 citations · 7 across the 10 of their papers we have counts for
13 papers
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
Sayan Biswas, Antoine Boutet, Davide Frey +7
Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the collaborative nature of DL make…
Mosaic Learning: A Framework for Decentralized Learning with Model Fragmentation
Sayan Biswas, Davide Frey, Romaric Gaudel +7
Decentralized learning (DL) enables collaborative machine learning (ML) without a central server, making it suitable for settings where training data cannot be centrally hosted. We…
Token-Efficient Change Detection in LLM APIs
Timothée Chauvin, Clément Lalanne, Erwan Le Merrer +3
Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-box access to model weights or g…
Log Probability Tracking of LLM APIs
Timothée Chauvin, Erwan Le Merrer, François Taïani +1
When using an LLM through an API provider, users expect the served model to remain consistent over time, a property crucial for the reliability of downstream applications and the r…
Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes
Augustin Godinot, Erwan Le Merrer, Camilla Penzo +2
The deployment of machine learning models in operational contexts represents a significant investment for any organisation. Consequently, the risk of these models being misappropri…
Asynchronous BFT Asset Transfer: Quasi-Anonymous, Light, and Consensus-Free
Timothé Albouy, Emmanuelle Anceaume, Davide Frey +4
This paper introduces a new asynchronous Byzantine-tolerant asset transfer system (cryptocurrency) with three noteworthy properties: quasi-anonymity, lightness, and consensus-freed…
Low-Cost Privacy-Preserving Decentralized Learning
Sayan Biswas, Davide Frey, Romaric Gaudel +5
Decentralized learning (DL) is an emerging paradigm of collaborative machine learning that enables nodes in a network to train models collectively without sharing their raw data or…
Under manipulations, are some AI models harder to audit?
Augustin Godinot, Gilles Tredan, Erwan Le Merrer +2
Auditors need robust methods to assess the compliance of web platforms with the law. However, since they hardly ever have access to the algorithm, implementation, or training data…
Near-Optimal Communication Byzantine Reliable Broadcast under a Message Adversary
Timothé Albouy, Davide Frey, Ran Gelles +5
We address the problem of Reliable Broadcast in asynchronous message-passing systems with nodes, of which up to are malicious (faulty), in addition to a message adversary t…
Process-Commutative Distributed Objects: From Cryptocurrencies to Byzantine-Fault-Tolerant CRDTs
Davide Frey, Lucie Guillou, Michel Raynal +1
This paper explores the territory that lies between best-effort Byzantine-Fault-Tolerant Conflict-free Replicated Data Types (BFT CRDTs) and totally ordered distributed ledgers, su…
Context Adaptive Cooperation
Timothé Albouy, Davide Frey, Mathieu Gestin +2
As shown by Reliable Broadcast and Consensus, cooperation among a set of independent computing entities (sequential processes) is a central issue in distributed computing. Consider…
A Modular Approach to Construct Signature-Free BRB Algorithms under a Message Adversary
Timothé Albouy, Davide Frey, Michel Raynal +1
This paper explores how reliable broadcast can be implemented without signatures when facing a dual adversary that can both corrupt processes and remove messages. More precisely, w…
Fisheye Consistency: Keeping Data in Synch in a Georeplicated World
Roy Friedman, Michel Raynal, François Taïani
Over the last thirty years, numerous consistency conditions for replicated data have been proposed and implemented. Popular examples of such conditions include linearizability (or…