OpenAI rolls out lockdown mode to fight prompt injection attacks
- 20 hours ago
- 1 min read
PC MAG — As AI use has skyrocketed in recent years, researchers are increasingly identifying prompt injection attacks as a critical security issue. These are attacks in which a bad actor misleads an AI model by injecting malicious instructions into a conversation, such as a PDF or website code designed to extract valuable company data.
Now, OpenAI is rolling out Lockdown Mode, an optional security setting that limits the ability of its products to connect to the web or external services. It does this by capping outbound network requests, though at the expense of some useful features. However, if you encounter malicious prompts, ChatGPT won't share any data with third parties, acting as a final line of defense.
Read the full story | PC MAG
