Getting class gradient not found while running other attacks except hop_skip_jump
Open
Type: Bug
- Dominant language
- Python
- Stars
- 938
- Forks
- 162
- PR merge metrics
- No merged PRs in 30d
Description
counterfit> set_target digits_mlp
digits_mlp> set_attack newtonfool
[+] success: Using 0e34bf51
digits_mlp>NewtonFool:0e34bf51> run
NewtonFool: 0%| | 0/1 [00:00
Contributor guide
No contributing guide indexed for this repository
Research direction
Reproduce the failure with the Counterfit commands in the issue, using the digits_mlp target and NewtonFool attack. Trace how the ART BlackBoxClassifier is used for attacks that require class_gradient, then verify that NewtonFool and the other affected attacks run without this error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100