Identifying Human Strategies for Generating Word-Level Adversarial Examples

20 Oct 2022  ·  Maximilian Mozes, Bennett Kleinberg, Lewis D. Griffin ·

Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality. Previous work found that human- and machine-generated adversarial examples are comparable in their naturalness and grammatical correctness. Most notably, humans were able to generate adversarial examples much more effortlessly than automated attacks. In this paper, we provide a detailed analysis of exactly how humans create these adversarial examples. By exploring the behavioural patterns of human workers during the generation process, we identify statistically significant tendencies based on which words humans prefer to select for adversarial replacement (e.g., word frequencies, word saliencies, sentiment) as well as where and when words are replaced in an input sequence. With our findings, we seek to inspire efforts that harness human strategies for more robust NLP models.

PDF Abstract
No code implementations yet. Submit your code now



Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.