duoergun0729 / duoergun0729/adversarial_examples
bug
Open
- Dominant language
- Jupyter Notebook
- Stars
- 276
- Forks
- 111
- PR merge metrics
- No merged PRs in 30d
Description
对5-fgm-tensorflow-pb中攻击后图像进行保存，重新输入到模型进行识别时，结果显示未攻击成功。
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the 5-fgm-tensorflow-pb example and reproduce the workflow of saving the attacked image before feeding it back into the model. Inspect the image-saving and re-input steps to determine why recognition reports that the attack failed; done means the reported behavior is explained and the issue's intended recognition result is reproducible.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100