SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs

Aldan Creo, Shushanta Pudasaini


Abstract
The advent of Large Language Models (LLMs) has enabled the generation of text that increasingly exhibits human-like characteristics. As the detection of such content is of significant importance, substantial research has been conducted with the objective of developing reliable AI-generated text detectors. These detectors have demonstrated promising results on test data, but recent research has revealed that they can be circumvented by employing different techniques. In this paper, we present homoglyph-based attacks (‘A’ → Cyrillic ‘А’) as a means of circumventing existing detectors. We conduct a comprehensive evaluation to assess the effectiveness of these attacks on seven detectors, including ArguGPT, Binoculars, DetectGPT, Fast-DetectGPT, Ghostbuster, OpenAI’s detector, and watermarking techniques, on five different datasets. Our findings demonstrate that homoglyph-based attacks can effectively circumvent state-of-the-art detectors, leading them to classify all texts as either AI-generated or human-written (decreasing the average Matthews Correlation Coefficient from 0.64 to -0.01). Through further examination, we extract the technical justification underlying the success of the attacks, which varies across detectors. Finally, we discuss the implications of these findings and potential defenses against such attacks.
Anthology ID:
2025.genaidetect-1.1
Volume:
Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Firoj Alam, Preslav Nakov, Nizar Habash, Iryna Gurevych, Shammur Chowdhury, Artem Shelmanov, Yuxia Wang, Ekaterina Artemova, Mucahid Kutlu, George Mikros
Venues:
GenAIDetect | WS
SIG:
Publisher:
International Conference on Computational Linguistics
Note:
Pages:
1–46
Language:
URL:
https://aclanthology.org/2025.genaidetect-1.1/
DOI:
Bibkey:
Cite (ACL):
Aldan Creo and Shushanta Pudasaini. 2025. SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs. In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect), pages 1–46, Abu Dhabi, UAE. International Conference on Computational Linguistics.
Cite (Informal):
SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs (Creo & Pudasaini, GenAIDetect 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.genaidetect-1.1.pdf