Defensive Dual Masking inserts and replaces tokens with [MASK] at training and inference, reporting higher adversarial accuracy than prior defenses on AGNews and MR.
In Findings of the Association for Computational Linguistics: ACL 2023, pages 7891–7906, Association for Computational Linguistics, Toronto, Canada
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Defensive Dual Masking for Robust Adversarial Defense
Defensive Dual Masking inserts and replaces tokens with [MASK] at training and inference, reporting higher adversarial accuracy than prior defenses on AGNews and MR.