Keep Apart Research Going: Donate Today
Oct 27, 2024
Robust Machine Unlearning for Dangerous Capabilities
Neel Jay, Austin Meek, Joshua Ehi
🏆 1st place by peer review
Summary
We test different unlearning methods to make models more robust against exploitation by malicious actors for the creation of bioweapons.
Cite this work:
@misc {
title={
Robust Machine Unlearning for Dangerous Capabilities
},
author={
Neel Jay, Austin Meek, Joshua Ehi
},
date={
10/27/24
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}