Opensource

1526 readers

80 users here now

A community for discussion about open source software! Ask questions, share knowledge, share news, or post interesting stuff related to it!

Credits

Icon base by Lorc under CC BY 3.0 with modifications to add a gradient

⠀

founded 1 year ago

MODERATORS

pylapp

Fake AI Buffer Overflow Risk in Curl report (hackerone.com)

submitted 1 week ago by [email protected] to c/opensource

12 comments fedilink hide all child comments

Now, with the help of AI, it's even easier to waste time of open source developers by creating fake security vulnerability reports.

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 3 points 1 week ago

Unfortunately, the methods of detecting AI generated text and training AI text generaters is basically identical. Any reliable method of detecting AI can therefore be used to improve its performance.

You can, at least, detect low grade attempts to use it. The default output has distinctive patterns. These can be detected. The problem is 2 fold. Firstly, some people write in the same way (the LLM is copying the amalgam, and they write close to that). Secondly, it's fairly trivial to ask the LLM to change its writing style.

No matter your method, you need to accept a high rate of both false positives and negatives.