Using transferable adversarial attacks like MIG and GRA inside AttEXplore raises insertion scores on ImageNet, but the best attack is chosen post hoc on the test set and deletion scores worsen.
The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Attribution for Enhanced Explanation with Transferable Adversarial eXploration
Using transferable adversarial attacks like MIG and GRA inside AttEXplore raises insertion scores on ImageNet, but the best attack is chosen post hoc on the test set and deletion scores worsen.