Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks

1 code implementation • 18 Feb 2024 • Yichen Wang, Shangbin Feng, Abe Bohan Hou, Xiao Pu, Chao Shen, Xiaoming Liu, Yulia Tsvetkov, Tianxing He

Our experiments reveal that almost none of the existing detectors remain robust under all the attacks, and all detectors exhibit different loopholes.

k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text

1 code implementation • 17 Feb 2024 • Abe Bohan Hou, Jingyu Zhang, Yichen Wang, Daniel Khashabi, Tianxing He

Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection.

Text Detection Text Generation

SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation

1 code implementation • 6 Oct 2023 • Abe Bohan Hou, Jingyu Zhang, Tianxing He, Yichen Wang, Yung-Sung Chuang, Hongwei Wang, Lingfeng Shen, Benjamin Van Durme, Daniel Khashabi, Yulia Tsvetkov

Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design.

Sentence Text Generation