Enhancing the Robustness of AI-Generated Text Detectors: A Survey

Xin Liu, Yang Li and Kan Li ()
Additional contact information
Xin Liu: School of Computer Science & Technology, Beijing Institute of Technology, No. 5, South Street, Zhongguancun, Beijing 100081, China
Yang Li: School of Computer Science & Technology, Beijing Institute of Technology, No. 5, South Street, Zhongguancun, Beijing 100081, China
Kan Li: School of Computer Science & Technology, Beijing Institute of Technology, No. 5, South Street, Zhongguancun, Beijing 100081, China

Mathematics, 2025, vol. 13, issue 13, 1-29

Abstract: In recent years, AI-generated text (AIGT) detection has attracted increasing attention, and some detectors demonstrate high accuracy in benchmark settings. However, the complexity and diversity of AIGT and counter-detection methods in real-world applications present substantial challenges for AIGT detection. Consequently, there is a growing demand for more robust AIGT detectors. This survey provides a systematic overview of existing research on enhancing the robustness of AIGT detectors. We categorize the focus of related literature into three key areas: text perturbation robustness, out-of-distribution (OOD) robustness, and AI–human hybrid text (AHT) detection robustness. For each area, we thoroughly summarize and analyze the corresponding robustness enhancement methods and additionally incorporate some approaches from other fields as a supplement. We also methodically organize relevant benchmark datasets, robustness evaluation methods, and metrics used to assess detectors’ performance. Then, through experiments, we evaluate the robustness of several commonly used detectors. Experiments show that text perturbations, OOD text, and AHT all affect the performance of these detectors, revealing that there remains significant room for improvement in their robustness. Finally, we suggest promising future directions based on the current issues faced by AIGT detectors and the detection requirements in real-world scenarios. To the best of our knowledge, this is the first review focused specifically on the robustness of AIGT detection.

Keywords: large language models; AI-generated text detection; model robustness (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/13/2145/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/13/2145/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:13:p:2145-:d:1691533

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().