News for hackers. Stuff that matters.

A comment on Planting Undetectable Backdoors in Machine Learning Models.

Re:Planting Undetectable Backdoors in Machine Learning Models by anton5mith2 on Saturday February 25, 2023 @03:52PM (#34940335)
“Sign in or purchase” seems like some archaic embargo on knowledge. Its 2023, really?
[ Parent | on HN ]
Re:Planting Undetectable Backdoors in Machine Learning Models by yazzku on Saturday February 25, 2023 @09:00PM (#34942326)
Tell Aaron Swartz about it.
[ Parent | on HN ]
Re:Planting Undetectable Backdoors in Machine Learning Models by p1esk on Saturday February 25, 2023 @09:54PM (#34942591)
A non-hardware related ML paper in IEEE is a yellow flag for me - typically these are papers rejected from good conferences (ICML, NeuroIPS, ICLR, etc).
[ Parent | on HN ]
Re:Planting Undetectable Backdoors in Machine Learning Models by polygamous_bat on Saturday February 25, 2023 @10:17PM (#34942717)
It's published in FOCS, which is one of the leading conferences in Theoretical CS. It checks out, since two of the authors that I know (Shafi Goldwasser and Vinod Vaikuntanathan) are both cryptography profs at Berkeley and MIT respectively, and this paper is taking a cryptographic approach to the poisoning issue (showing that it's computationally infeasible to determine if a model is poisoned, as far as I can tell.)
[ Parent | on HN ]
Re:Planting Undetectable Backdoors in Machine Learning Models by cryptohell on Sunday February 26, 2023 @12:25AM (#34943297)
(A Turing award winner and a Godel prize winner professors at Berkeley and MIT)
[ Parent | on HN ]