ChatGPT Security: Lockdown Mode Fights Prompt Injection

OpenAI has launched a new security feature called Lockdown Mode for ChatGPT. This mode aims to protect against "prompt injection attacks" that can hijack AI systems and steal personal information. What's interesting is that these attacks have previously compromised AI browsers like Perplexity and controlled smart home devices through Google Gemini. Lockdown Mode restricts features such as live web browsing and Deep Research across all ChatGPT plans. However, OpenAI acknowledges that risks from uploaded files still remain. This new feature is rolling out to all ChatGPT account types, including Free, Go, Plus, and Pro plans. This matters because it offers an important layer of defense for your AI interactions.