AdvChar is a character-level black-box attack that uses interpreter importance scores to pick tokens, fooling NLP classifiers while keeping post-hoc explanations similar.
Grad-cam: Visual explanations from deep networks via gradient-based localization,
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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Attacking interpretable NLP systems
AdvChar is a character-level black-box attack that uses interpreter importance scores to pick tokens, fooling NLP classifiers while keeping post-hoc explanations similar.