Home / Focus Areas / Global Catastrophic Risks / Potential Risks from Advanced Artificial Intelligence

Error message

Warning: Use of undefined constant openphil_social - assumed 'openphil_social' (this will throw an Error in a future version of PHP) in openphil_social_block_block_view() (line 90 of /var/www/html/openphil/live/sites/all/modules/custom/openphil_social_block/openphil_social_block.module).

Massachusetts Institute of Technology — Adversarial Robustness Research

Organization Name 
Massachusetts Institute of Technology
Award Date 
2/2021
Grant Amount 
$1,430,000
Purpose 
To support research on adversarial robustness as a means to improve AI safety.
Topic (focus area) 
Potential Risks from Advanced Artificial Intelligence

Grant Investigator: Catherine Olsson and Daniel Dewey

This page was reviewed but not written by the grant investigators. Massachusetts Institute of Technology staff also reviewed this page prior to publication.

Open Philanthropy recommended a grant of $1,430,000 over three years to the Massachusetts Institute of Technology to support research by Professor Aleksander Madry on adversarial robustness as a means to improve AI safety.

This falls within our focus area of potential risks from advanced artificial intelligence.