ChatGPT adds Lockdown Mode to protect sensitive data
OpenAI's new setting disables some features so prompt injection attacks can't steal sensitive data.
The problem
Prompt injection hides malicious instructions in web pages or files so an AI follows them, for example to leak data.
What Lockdown Mode does
Lockdown Mode in ChatGPT disables:
- Live web browsing (cached content only).
- Retrieving and displaying web images (image generation still works).
- Deep research and agent mode.
OpenAI says it's "designed for people and organizations that handle sensitive data."
Availability
Self-serve ChatGPT Business accounts and eligible personal accounts.
Caveat
TechCrunch notes ChatGPT may still be vulnerable to prompt injection even with it on.
Founder and editor-in-chief of Kurd Developers. Phone and tech news on YouTube, Instagram and TikTok.
More stories
One text can break your phone: Android's 'SMS of Death' explained
A flaw in Android 12 and later lets a specially crafted SMS drop calls and even make a phone unusable. The fix is in October's security patch.
GTA VI lands November 19: prices, editions and what to know
Rockstar has locked the date: Thursday, November 19 on PS5 and Xbox Series X|S. Standard costs $79.99 and Ultimate $99.99.
Apple's first touchscreen MacBook Pro brings OLED and Dynamic Island
The new PROLED XDR display responds to touch, the notch is gone and Dynamic Island takes its place. Prices start at $2,899.
The $1,999 iPhone Duo Has a Black-Bar Problem, and Fixing It Is Harder Than It Looks
Apple's first foldable is a hardware flex. But unfold it and many of your apps shrink into a phone-shaped window floating in black. Here's why the app world wasn't ready, and why developers can't just hit "stretch".