Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[D] Paper Analysis - Scalable Extraction of Training Data from (Production) Language Models (Video Walkthrough) (alien.top)

submitted 11 months ago by ykilcher@alien.top to c/machinelearning@academy.garden

2 comments fedilink hide all child comments

https://youtu.be/KwpeuqT69fw

Researchers were able to get giant amounts of training data out of ChatGPT by simply asking it to repeat a word many times over, which causes the model to diverge and start spitting out memorized text.

Why does this happen? And how much of their training data do such models really memorize verbatim?

OUTLINE:

0:00 - Intro

8:05 - Extractable vs Discoverable Memorization

14:00 - Models leak more data than previously thought

20:25 - Some data is extractable but not discoverable

25:30 - Extracting data from closed models

30:45 - Poem poem poem

37:50 - Quantitative membership testing

40:30 - Exploring the ChatGPT exploit further

47:00 - Conclusion

Paper: https://arxiv.org/abs/2311.17035

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

[–] we_are_mammals@alien.top 1 points 11 months ago

Can't OpenAI simply check the output for sharing long substrings with the training data (perhaps probabilistically)?