BERTGuard: Robust Text Classification against Adversarial Attacks
This paper introduces BERTGuard, a text classification framework that enhances the resilience of BERT models against adversarial attacks through feature trimming and sub-sampling within an adversarial training framework. Our approach outperforms the b
Authors
- Tahir Ekin (ORCID: https://orcid.org/0000-0002-0965-3521)
- Laxmi Shaw (ORCID: https://orcid.org/0000-0002-8238-1999)
- Mohd Shaban Ansari (ORCID: https://orcid.org/0000-0002-1481-4940)
Publication Details
- Published
- 2024-09-05
- DOI
- https://doi.org/10.22541/au.172556904.43002725/v1
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00