|
Navigation
Recherche
|
The Security Hole at the Heart of ChatGPT and Bing
jeudi 25 mai 2023, 08:00 , par Wired: Tech.
Indirect prompt-injection attacks can leave people vulnerable to scams and data theft when they use the AI chatbots.
https://www.wired.com/story/chatgpt-prompt-injection-attack-security/
|
56 sources (32 en français)
Date Actuelle
dim. 11 mai - 04:29 CEST
|
Lire la suite sur Wired: Tech.