Relearning what success means for machine unlearning
A. Feder Cooper ⋅ Christopher Choquette Choo ⋅ Ken Ziyu Liu ⋅ Amy Cyphert ⋅ Mark Lemley ⋅ Miranda Bogen ⋅ Matthew Jagielski ⋅ Seth Neel ⋅ Niloofar Mireshghallah ⋅ Lama Ahmad ⋅ James Grimmelmann ⋅ David Bau ⋅ Vitaly Shmatikov ⋅ Fernando Delgado ⋅ Chris De Sa ⋅ Katja Filippova ⋅ Nicolas Papernot ⋅ Katherine Lee
Abstract
Machine unlearning has garnered a lot of interest within the research community, and several survey papers in addition to hundreds of research papers have been written about it. Our paper revisits the goals of machine unlearning to propose a new way of breaking down the problem (identifying unlearning targets) that clarify both the goals of machine unlearning and our methods of verifying the success of machine unlearning.
Chat is not available.
Successful Page Load