bethgelab / bethgelab/foolbox

criteria: Misclassification

Open
#734 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3k
Forks
442
PR merge metrics
No merged PRs in 30d

Description

There are two ways to use the API:

To use the criteria:
```python
raw_advs, clipped_advs, success = attack(fmodel, data, criterion=Misclassification(label), epsilons=args.eps)
```

and without using the criteria:
```python
raw_advs, clipped_advs, success = attack(fmodel, data, label, epsilons=args.eps)
```

What is the difference?
Unfortunately, haven't found examples anywhere.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.