Defensive Sufficiency in a Stackelberg Model of AI Security
A Stackelberg model finds when red-team feedback and repairs suffice to defend finite AI attack surfaces.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
A Stackelberg model finds when red-team feedback and repairs suffice to defend finite AI attack surfaces.
Today 18 readers · 18 views · 0 reads · all time 108K views