Pith. sign in

Recent advances in deep learning based dialogue systems: A systematic survey,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CR 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Attacking interpretable NLP systems

cs.CR · 2025-07-22 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Attacking interpretable NLP systems cs.CR · 2025-07-22 · conditional · none · ref 3

    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.