On the Impossible Safety of Large AI Models

no code implementations • 30 Sep 2022 • El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Lê-Nguyên Hoang, Rafael Pinot, Sébastien Rouault, John Stephan

Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance.

Privacy Preserving

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

1 code implementation • 17 Feb 2022 • Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang, Oscar Villemaud

More specifically, we prove that every gradient attack can be reduced to data poisoning, in any personalized federated learning system with PAC guarantees (which we show are both desirable and realistic).

Data Poisoning Personalized Federated Learning

Strategyproof Learning: Building Trustworthy User-Generated Datasets

1 code implementation • 4 Jun 2021 • Sadegh Farhadkhani, Rachid Guerraoui, Lê-Nguyên Hoang

We prove in this paper that, perhaps surprisingly, incentivizing data misreporting is not a fatality.

Fairness

Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments

no code implementations • 29 May 2021 • Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo, Sergei Volodin, Dalia Papuc, Orfeas Liossatos, Ben Crulis, Mariame Tighanimine, Isabela Constantin, Anastasiia Kucherenko, Alexandre Maurer, Felix Grimberg, Vlad Nitu, Chris Vossen, Sébastien Rouault, El-Mahdi El-Mhamdi

We outline the structure of the Tournesol database, the key features of the Tournesol platform and the main hurdles that must be overcome to make it a successful project.