OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
中文摘要
OpenAI推出锁定模式以防范提示词注入攻击，旨在降低敏感数据泄露的风险。
English Summary
OpenAI introduces Lockdown Mode to mitigate sensitive data leakage risks from prompt injection attacks.
原文节选
Even with Lockdown Mode, ChatGPT could be still vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.