“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks
Edoardo Mosca, Shreyash Agarwal, Javier Rando Ramírez, Georg Groh
Abstract
Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in computer vision has been carried to develop reliable defense strategies. However, the same issue remains less explored in natural language processing. Our work presents a model-agnostic detector of adversarial text examples. The approach identifies patterns in the logits of the target classifier when perturbing the input text. The proposed detector improves the current state-of-the-art performance in recognizing adversarial inputs and exhibits strong generalization capabilities across different NLP models, datasets, and word-level attacks.- Anthology ID:
- 2022.acl-long.538
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7806–7816
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.538
- DOI:
- 10.18653/v1/2022.acl-long.538
- Cite (ACL):
- Edoardo Mosca, Shreyash Agarwal, Javier Rando Ramírez, and Georg Groh. 2022. “That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7806–7816, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- “That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks (Mosca et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.acl-long.538.pdf
- Data
- AG News, IMDb Movie Reviews