OpenFlux
Retour aux articles
OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
IA Programmation Web

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

TechCrunch ·

Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.

Lire l'article original

Articles similaires