Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2305.04067 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916187230699520 |
|---|---|
| author | Yang, Heng Li, Ke |
| author_facet | Yang, Heng Li, Ke |
| contents | Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods struggle to effectively repair the semantics in adversarial examples, resulting in unsatisfactory performance and limiting their practical utility. To repair the semantics in adversarial examples, we introduce a novel approach named Reactive Perturbation Defocusing (Rapid). Rapid employs an adversarial detector to identify fake labels of adversarial examples and leverage adversarial attackers to repair the semantics in adversarial examples. Our extensive experimental results conducted on four public datasets, convincingly demonstrate the effectiveness of Rapid in various adversarial attack scenarios. To address the problem of defense performance validation in previous works, we provide a demonstration of adversarial detection and repair based on our work, which can be easily evaluated at https://tinyurl.com/22ercuf8. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_04067 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples Yang, Heng Li, Ke Computation and Language Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods struggle to effectively repair the semantics in adversarial examples, resulting in unsatisfactory performance and limiting their practical utility. To repair the semantics in adversarial examples, we introduce a novel approach named Reactive Perturbation Defocusing (Rapid). Rapid employs an adversarial detector to identify fake labels of adversarial examples and leverage adversarial attackers to repair the semantics in adversarial examples. Our extensive experimental results conducted on four public datasets, convincingly demonstrate the effectiveness of Rapid in various adversarial attack scenarios. To address the problem of defense performance validation in previous works, we provide a demonstration of adversarial detection and repair based on our work, which can be easily evaluated at https://tinyurl.com/22ercuf8. |
| title | The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2305.04067 |