OpenAI announces new Lockdown Mode to prevent prompt injection attacks
Key takeaways
- The new Lockdown Mode will disable live web browsing, meaning users can only access cached content.
- The primary objective of Lockdown Mode is to reduce the risk of sensitive data being inadvertently shared.
- READ MORE: Trump administration explores taking an equity stake in OpenAI
Why this matters: local context for readers following news across Pakistan and the region.
Add ARY News on Google AAResize Open AI has announced a new feature aimed at providing additional protection against prompt injection attacks, where malicious instructions for chatbots are embedded in web pages and other content sources.
The new Lockdown Mode will disable live web browsing, meaning users can only access cached content. It will also prevent the retrieval and display of images from the web (although users can still generate images) and limit deep research and agent mode functionality.
However, OpenAI cautions that even with Lockdown Mode activated, ChatGPT may still be vulnerable to prompt injections originating from cached web content or uploaded files, which could affect the behavior or accuracy of its responses.