ChatGPT can offer coding solutions, but its tendency for hallucination presents attackers with an opportunity. Here's what we learned.

“* People ask LLMs to write code

LLMs recommend imports that don’t actually exist
Attackers work out what these imports’ names are, and create & upload them with malicious payloads
People using LLM-written code then auto-add malware themselves”

  • Haus@kbin.social
    1·
    2 years ago

    This is pretty much my experience. It did a pretty good job with the grunt work of setting up a Qt UI in python, but something like 5/20 imports were wrong.