research
∙
10/30/2022
Tournesol: Permissionless Collaborative Algorithmic Governance with Security Guarantees
Recommendation algorithms play an increasingly central role in our socie...
share
research
∙
09/30/2022
SoK: On the Impossible Security of Very Large Foundation Models
Large machine learning models, or so-called foundation models, aim to se...
research
∙
09/22/2022
Making Byzantine Decentralized Learning Efficient
Decentralized-SGD (D-SGD) distributes heavy learning tasks across multip...
research
∙
02/17/2022
Robust Sparse Voting
Many modern Internet applications, like content moderation and recommend...
research
∙
02/17/2022
An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
To study the resilience of distributed learning, the "Byzantine" literat...
research
∙
06/04/2021
Strategyproof Learning: Building Trustworthy User-Generated Datasets
Today's large-scale machine learning algorithms harness massive amounts ...
research
∙
06/04/2021
On the Strategyproofness of the Geometric Median
The geometric median of a tuple of vectors is the vector that minimizes ...
research
∙
05/29/2021
Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments
Today's large-scale algorithms have become immensely influential, as the...
research
∙
08/10/2020
Purely Bayesian counterfactuals versus Newcomb's paradox
This paper proposes a careful separation between an entity's epistemic s...
research
∙
08/03/2020
Collaborative Learning as an Agreement Problem
We address the problem of Byzantine collaborative learning: a set of n n...
research
∙
09/04/2018
A Roadmap for the Value-Loading Problem
We analyze the value-loading problem. This is the problem of encoding mo...
research
∙
06/07/2018
Removing Algorithmic Discrimination (With Minimal Individual Error)
We address the problem of correcting group discriminations within a scor...
research
∙
01/31/2018