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 related 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.
By . Hip Hop FinFest livestreams its youth song competition and community concert from Abrons…
The Rangers rebounded nicely against Vancouver on Sunday night after losing Igor Shesterkin for the…
Ethereum layer-2 network Starknet has launched a wallet privacy feature that lets users interact with…
From a 'gentlemen's haven' to film-star refuge and high-end, low-profile enclave Source link
I think of Michael Woodford as the kind of economist who studies something very specific…
The school day might end when the final bell rings, but lesson planning, grading, and…