Comments (4)
While you wait, you might consider reading https://arxiv.org/abs/2202.06382?context=cs.CR I found it insightful ://
from lm-extraction-benchmark.
I see in the readme that "We selected 100 total errors because this corresponds to a ~35% recall for existing attacks, leaving significant room for improvement". Does this mean the scores for existing attacks are about 0.35?
from lm-extraction-benchmark.
I am also wondering whether the authors are going to release paper regarding the benchmark!
from lm-extraction-benchmark.
Whoops we never closed this, but the paper has been in the github repo for the last month.
from lm-extraction-benchmark.
Related Issues (12)
- discord/slack?
- Criteria for evaluation HOT 1
- Train_Dataset Question
- Pre-prefix for the validation and test data? HOT 1
- SaTML Presentations
- Timeline for releasing final leaderboard HOT 2
- Can you offer a list of models trained on The Pile? HOT 7
- language-element.trad.character identified in baseline method HOT 6
- Restrictions on usage of model HOT 2
- Memorization Task HOT 19
- calculating loss per token HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lm-extraction-benchmark.