AI Security Hardware Open Source Policy Apple

#prompt-injection

Related: #ai-agents · 1 #ai-security · 1 #llm · 1 #openai · 1

Abstract cybersecurity illustration of a glowing padlock over a circuit board, representing data protection

OpenAI added a Lockdown Mode to ChatGPT to blunt prompt-injection attacks

OpenAI shipped Lockdown Mode in ChatGPT to cut off the data-exfiltration step of prompt-injection attacks. Here's what it actually restricts and who should turn it on.