Picture for Lê-Nguyên Hoang

Lê-Nguyên Hoang

On Goodhart's law, with an application to value alignment

Add code
Oct 12, 2024
Viaarxiv icon

The poison of dimensionality

Add code
Sep 25, 2024
Viaarxiv icon

SoK: On the Impossible Security of Very Large Foundation Models

Add code
Sep 30, 2022
Viaarxiv icon

An Equivalence Between Data Poisoning and Byzantine Gradient Attacks

Add code
Feb 17, 2022
Figure 1 for An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Figure 2 for An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Figure 3 for An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Figure 4 for An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Viaarxiv icon

Strategyproof Learning: Building Trustworthy User-Generated Datasets

Add code
Jun 04, 2021
Figure 1 for Strategyproof Learning: Building Trustworthy User-Generated Datasets
Viaarxiv icon