OpenAI announced a new feature that it says will provide additional protection from prompt injection attacks, where malicious chatbot instructions are hidden in webpages and other content sources.
Among other things, Lockdown Mode will disable live web browsing (so you can only access cached content), the retrieval and display of images from the web (you can still generate images), deep research, and agent mode.
The company says that even with Lockdown Mode turned on, ChatGPT could still be vulnerable to prompt injections — which could, for example, “appear in cached web content or in an uploaded file, and could still affect the behavior or accuracy of a response.”
But the goal is to reduce the likelihood that sensitive data gets shared in the process.
“Lockdown Mode is not intended for everyone,” OpenAI says. “It is designed for people and organizations that handle sensitive data and want stricter protection from data exfiltration risks to prompt injection.”
The company says it’s currently rolling Lockdown Mode out to self-serve ChatGPT Business accounts, as well as eligible personal accounts.
-
Carlo Ancelotti and Brazil: A World Cup dream partnership or a flawed Selecao beyond saving?
-
Italy’s Front Pages: Juventus Chase Sorloth as Inter Map Out Triple Defensive Move
-
‘That goal against England was unbelievable – one of the defining moments of my career so far’: Nico Williams reflects on his Euro 2024 final strike
-
USMNT’s Antonee ‘Jedi’ Robinson nets stunning long-range goal against Germany in final World Cup warm-up
-
Chelsea’s £21m offer for Swedish prodigy accepted as Arsenal face setback in Alvarez chase – Transfer Round-up
