S-GBT introduces a Hessian-bounding tensor and associated regularization for LSTM and CNN models that yields tighter certified robustness bounds against word substitutions, improving robust accuracy by up to 23.4%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP
S-GBT introduces a Hessian-bounding tensor and associated regularization for LSTM and CNN models that yields tighter certified robustness bounds against word substitutions, improving robust accuracy by up to 23.4%.