@inproceedings{tonni-etal-2025-odd,
    title = "Some Odd Adversarial Perturbations and the Notion of Adversarial Closeness",
    author = "Tonni, Shakila Mahjabin  and
      Faustini, Pedro  and
      Dras, Mark",
    editor = "Kummerfeld, Jonathan K.  and
      Joshi, Aditya  and
      Dras, Mark",
    booktitle = "Proceedings of The 23rd Annual Workshop of the Australasian Language Technology Association",
    month = nov,
    year = "2025",
    address = "Sydney, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-alta/2025.alta-main.3/",
    pages = "28--44",
    ISBN = "1834-7037",
    abstract = "Deep learning models for language are vulnerable to adversarial examples. However, the perturbations introduced can sometimes seem odd or very noticeable to humans, which can make them less effective, a notion captured in some recent investigations as a property of `(non-)suspicion'. In this paper, we focus on three main types of perturbations that may raise suspicion: changes to named entities, inconsistent morphological inflections, and the use of non-English words. We define a notion of adversarial closeness and collect human annotations to construct two new datasets. We then use these datasets to investigate whether these kinds of perturbations have a disproportionate effect on human judgements. Following that, we propose new constraints to include in a constraint-based optimisation approach to adversarial text generation. Our human evaluation shows that these do improve the process by preventing the generation of especially odd or marked texts."
}