Abstract:The recent large-scale emergence of LLMs has left an open space for dealing with their consequences, such as plagiarism or the spread of false information on the Internet. Coupling this with the rise of AI detector bypassing tools, reliable machine-generated text detection is in increasingly high demand. We investigate the paraphrasing attack resilience of various machine-generated text detection methods, evaluating three approaches: fine-tuned RoBERTa, Binoculars, and text feature analysis, along with their ensembles using Random Forest classifiers. We discovered that Binoculars-inclusive ensembles yield the strongest results, but they also suffer the most significant losses during attacks. In this paper, we present the dichotomy of performance versus resilience in the world of AI text detection, which complicates the current perception of reliability among state-of-the-art techniques.
| Comments: | NAACL 2025 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.14240 [cs.LG] |
| (or arXiv:2605.14240v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14240 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.18653/v1/2025.naacl-srw.46
DOI(s) linking to related resources |
Submission history
From: Andrii Shportko [view email]
[v1]
Thu, 14 May 2026 01:12:34 UTC (5,635 KB)