Trigger color significantly affects semantic backdoor attack success in federated learning on CelebA hair-color classification, with white triggers better for blond targets and black for black targets.
arXiv preprint arXiv:2012.06917 (2020)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Composite three-channel preprocessing of SDO/AIA images yields a YOLOv5 prominence detector with mAP@50 of 0.749 and 78% recall that also generalizes to SUVI data.
citing papers explorer
-
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
Trigger color significantly affects semantic backdoor attack success in federated learning on CelebA hair-color classification, with white triggers better for blond targets and black for black targets.
-
A Robust Deep Learning Framework for Prominence Detection through Composite Feature Representations
Composite three-channel preprocessing of SDO/AIA images yields a YOLOv5 prominence detector with mAP@50 of 0.749 and 78% recall that also generalizes to SUVI data.
- Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition