OpenAI Help: Lockdown Mode
Read OriginalThis article discusses OpenAI's new Lockdown Mode feature, which is rolling out to eligible personal and self-serve ChatGPT Business accounts. Lockdown Mode aims to prevent the final stage of data exfiltration during prompt injection attacks by limiting outbound network requests. It does not stop prompt injections from appearing but blocks data transmission to attackers. The article explains how this addresses the 'Lethal Trifecta' of LLM security risks and notes tradeoffs in functionality for users with elevated risk profiles.
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser
Top of the Week
No top articles yet