Create an overlaid diverging histogram for extraction #35
Labels
extraction
Related to model extraction attacks
metrics visualization
Part of the three phase metrics visualization project
needs validation
Some validation is required to document the solution
user-facing
Features that will directly impact users
Is your feature request related to a problem? Please describe.
It is difficult to reason about the difference between a victim and substitute model from a simple label agreement score.
Describe the solution you'd like.
Create an overlaid diverging histogram that showcases the correct and incorrect responses on a single axis.
Describe alternatives you've considered.
If a better solution is available, please comment on this issue.
Detail any additional context.
This was inspired by Figure 3 of Understanding and Visualizing Data Iteration in Machine Learning.
The text was updated successfully, but these errors were encountered: