Navigation
Search
|
Machine-learning models vulnerable to undetectable backdoors: new claim
Thursday April 21, 2022. 09:24 AM , from 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/
|
25 sources
Current Date
Apr, Fri 26 - 01:38 CEST
|