Residue-Based Natural Language Adversarial Attack Detection

Vyas Raina, Mark Gales


Abstract
Deep learning based systems are susceptible to adversarial attacks, where a small, imperceptible change at the input alters the model prediction. However, to date the majority of the approaches to detect these attacks have been designed for image processing systems. Many popular image adversarial detection approaches are able to identify adversarial examples from embedding feature spaces, whilst in the NLP domain existing state of the art detection approaches solely focus on input text features, without consideration of model embedding spaces. This work examines what differences result when porting these image designed strategies to Natural Language Processing (NLP) tasks - these detectors are found to not port over well. This is expected as NLP systems have a very different form of input: discrete and sequential in nature, rather than the continuous and fixed size inputs for images. As an equivalent model-focused NLP detection approach, this work proposes a simple sentence-embedding “residue” based detector to identify adversarial examples. On many tasks, it out-performs ported image domain detectors and recent state of the art NLP specific detectors.
Anthology ID:
2022.naacl-main.281
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3836–3848
Language:
URL:
https://aclanthology.org/2022.naacl-main.281
DOI:
10.18653/v1/2022.naacl-main.281
Bibkey:
Cite (ACL):
Vyas Raina and Mark Gales. 2022. Residue-Based Natural Language Adversarial Attack Detection. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3836–3848, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Residue-Based Natural Language Adversarial Attack Detection (Raina & Gales, NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.281.pdf
Code
 rainavyas/naacl-2022-residue-detector
Data
AG NewsIMDb Movie Reviews