Token-Ensemble text generation: On attacking the automatic AI-generated text detection

F Huang, H Kwak, J An - arXiv preprint arXiv:2402.11167, 2024 - arxiv.org
The robustness of AI-content detection models against cultivated attacks (eg, paraphrasing
or word switching) remains a significant concern. This study proposes a novel token …
被引用次数：2 相关文章

Token-Ensemble Text Generation: On Attacking the Automatic AI-Generated Text Detection

F Huang, H Kwak, J An - arXiv e-prints, 2024 - ui.adsabs.harvard.edu
The robustness of AI-content detection models against cultivated attacks (eg, paraphrasing
or word switching) remains a significant concern. This study proposes a novel token …