Adversarial-Deep-Learning / Adversarial-Deep-Learning/code-soup
Visual Perturbation Metrics
Đang mở
good first issue
Implementation
Priority:High
- Ngôn ngữ chính
- Jupyter Notebook
- Star
- 17
- Fork
- 17
- Chỉ số merge pull request
- Không có pull request nào được merge trong 30 ngày
Mô tả
For evasive whitebox or blackbox attacks, the objective of each attack is to fool the model to predict a different class but making it deceptive by making small changes, these changes are measured in distances for Example the L1/L2 Norm of difference.
Implement these metrics
- [x] L1, L2 ... Lk Norm
- [ ] ISSM
- [ ] PSNR
- [x] SAM
- [x] SRE
You can find numpy and cv2 implementation at https://github.com/up42/image-similarity-measures/blob/master/image_similarity_measures/quality_metrics.py
Hướng dẫn đóng góp
Đánh giá
Issue này chưa được đánh giá.