This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
ApartSprints
AI Policy Hackathon at Johns Hopkins University
670822f88b8fdf04a35a4b76
AI Policy Hackathon at Johns Hopkins University
October 28, 2024
Accepted at the 
670822f88b8fdf04a35a4b76
 research sprint on 

Robust Machine Unlearning for Dangerous Capabilities

We test different unlearning methods to make models more robust against exploitation by malicious actors for the creation of bioweapons.

By 
Neel Jay, Austin Meek, Joshua Ehi
🏆 
4th place
3rd place
2nd place
1st place
 by peer review
Thank you! Your submission is under review.
Oops! Something went wrong while submitting the form.

This project is private