|
Navigation
Recherche
|
Boffins devise 'universal backdoor' for image models to cause AI hallucinations
mercredi 6 décembre 2023, 02:15 , par TheRegister
Data poisoning appears open to all
Three Canada-based computer scientists have developed what they call a universal backdoor for poisoning large image classification models.…
https://go.theregister.com/feed/www.theregister.com/2023/12/06/universal_backdoor_llm_image/
|
56 sources (32 en français)
Date Actuelle
sam. 10 mai - 12:26 CEST
|
Lire la suite sur TheRegister