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.
[ad_2]
Source link
More on openai unveils lockdown mode to protect
Stay tuned for updates on openai unveils lockdown mode to protect as the story develops. Related: Mobile & Accessories.
Frequently Asked Questions
A new feature providing additional protection from prompt injection attacks, where malicious chatbot instructions are hidden in webpages and other content sources.
Live web browsing (only cached content), retrieval and display of images from the web (image generation still works), deep research, and agent mode.
No. OpenAI says ChatGPT could still be vulnerable – injections could appear in cached web content or uploaded files and affect responses. The goal is reducing the likelihood of sensitive data being shared.
It is designed for people and organizations handling sensitive data who want stricter protection. It is rolling out to self-serve ChatGPT Business accounts and eligible personal accounts.
