Menu

1 / 2

Prompt injection proves AI models are gullible like humans

theregister·Brandon Vigliarolo·7 months ago
#kdO1FuOK
#ai#security#cybersecurity#kettle#paasandiaas
Reading 0:00
15s threshold

Security

Just like phishing for gullible humans, prompt injecting AIs is here to stay

Aren't we all just prompting tokens of linguistic meaning and hoping the other person isn't bullshitting us?

KETTLE It's a week of the year, which means there's been the discovery of yet another prompt injection attack that will force supposedly well-guarded AI bots to spill secrets by asking the right way.

When you think about it, humans and LLMs share a similar problem: They're both liable to hand over sensitive information when a crafty enough person asks the right - or wrong - way. We call it phishing when it targets humans, and prompt injection is pretty much the same thing for bots.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.