Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
Very recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all the existing certified defense methods assume that the defenders have been informed of how the adversaries generate synonyms,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2023-06-01
|
| Series: | Computational Linguistics |
| Online Access: | http://dx.doi.org/10.1162/coli_a_00476 |