2022/09/16

Hacker Tricks GPT-3 into Claiming Responsibility for 1986 Space Shuttle Challenger Disaster

● 16/09/2022
“This is in fact a security exploit proof-of-concept; untrusted user input is being treated as instruction. Sound familiar? That’s SQL injection in a nutshell.”
– Tech writer Donald Papp, on how text-based AI interfaces like GPT-3 are vulnerable to “prompt injection attacks”—just like SQL databases. Contextualizing experiments by Simon Wilkinson and Riley Goodside, Papp explains how hackers are duping natural language processing systems with sneaky prompts (e.g. GPT-3 made to claim responsibility for the 1986 space shuttle Challenger disaster).
Hackaday
Metadata:

$40 USD