ChatGPT's new Lockdown Mode can stop prompt injection - here's how it works
SMRTR summary
OpenAI launched Lockdown Mode for ChatGPT Enterprise users to combat prompt injection attacks, where hackers insert malicious code into AI prompts to steal confidential data. The security feature restricts ChatGPT's interactions with external systems and disables risky capabilities like web browsing, while new Elevated Risk labels warn users about potentially dangerous tools and content.
SMRTR provides this summary for quick context. The original article belongs to ZDNet.
Read the original article