# “That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks

> Research article (Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022) · cited 27× · AI/ML

**Wikidata**: [openalex:W4223913581](https://www.wikidata.org/wiki/openalex:W4223913581)  
**Source**: https://4ort.xyz/entity/that-is-a-suspicious-reaction-interpreting-logits-variation-to-detect-nlp-adversarial-attacks