ChatGPT Lockdown Mode: New Security Feature Explained

ChatGPT has introduced a new security feature called Lockdown Mode. This mode aims to reduce the risk of sensitive data exposure from prompt injection attacks. These attacks involve malicious instructions embedded in webpages or other external content that a chatbot might process. OpenAI, the company behind ChatGPT, states this feature is for users handling sensitive information. When activated, Lockdown Mode disables live web browsing, access to internet images, deep research tools, and agent-style functions. Users can still generate images, but the model will only access cached web content, not real-time browsing. OpenAI acknowledges this feature doesn't completely eliminate the underlying risk. For instance, a prompt injection could still appear in cached web content or uploaded files. Lockdown Mode is rolling out to self-serve ChatGPT Business accounts and eligible personal users. It can be found in the Security section under Advanced security settings. It cannot be used at the same time as Developer Mode. This matters because it offers a new layer of protection for sensitive information when using ChatGPT.