Are AI-Generated Text Detectors Robust to Adversarial Perturbations?

v1v2 (latest)

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?

3 June 2024

ArXiv (abs)PDF HTML Github (28★)

Papers citing "Are AI-Generated Text Detectors Robust to Adversarial Perturbations?"

5 / 5 papers shown

Title
On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text? Mingmeng Geng Thierry Poibeau DeLMO 44 0 0 23 Oct 2025
A Mathematical Theory of Discursive Networks Juan B. Gutiérrez 147 0 0 09 Jul 2025
Explainability-Based Token Replacement on LLM-Generated Text Hadi Mohammadi Anastasia Giachanou Daniel L. Oberski Ayoub Bagheri DeLMO 189 1 0 04 Jun 2025
Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbationsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 Yunlong Zhou Juan Wen Wanli Peng Yiming Xue Ziwei Zhang Zhengxian Wu AAML 174 0 0 22 Apr 2025
Could AI Trace and Explain the Origins of AI-Generated Images and Text? Hongchao Fang Yixin Liu Ran Xu Can Qin Rahul Gupta Feng Liu Lichao Sun Dongwon Lee Lifu Huang Wenpeng Yin DeLMO 283 0 0 05 Apr 2025