Augustin Godinot
@augodinot
Algorithm Auditing | CS PhD student @ INRIA/IRISA/PEReN | Visiting UofT @ CleverHans Lab !
ID: 2534826802
http://grodino.github.io 08-05-2014 08:35:17
95 Tweet
95 Takipçi
381 Takip Edilen
Trustworthy ML Initiative (TrustML) ICML Conference Current incentives for "Trustwortyness" are reputational. Thus, models developers only need to fake it. We present a research direction to prevent this: x.com/augodinot/stat…