Navigation
Recherche
|
Machine-learning models vulnerable to undetectable backdoors: new claim
jeudi 21 avril 2022, 09:24 , par TheRegister
It's 2036 and another hijacked AI betrays its operators
Boffins from UC Berkeley, MIT, and the Institute for Advanced Study in the United States have devised techniques to implant undetectable backdoors in machine learning (ML) models.…
https://go.theregister.com/feed/www.theregister.com/2022/04/21/machine_learning_models_backdoors/
|
56 sources (32 en français)
Date Actuelle
mer. 24 avril - 03:53 CEST
|