Under FGSM and BIM attacks, EfficientNetV2B0 accuracy drops from 89.94% to 58.73% and 45.50%, while explanation IoU and RMSE scores against SAM masks change only slightly.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Impact of Adversarial Attacks on Deep Learning Model Explainability
Under FGSM and BIM attacks, EfficientNetV2B0 accuracy drops from 89.94% to 58.73% and 45.50%, while explanation IoU and RMSE scores against SAM masks change only slightly.