Frustratingly Easy Edit-based Linguistic Steganography with a Masked
Language Model

Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model

20 April 2021

Sadao Kurohashi

Papers citing "Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model"

7 / 7 papers shown

Title
Watermark Smoothing Attacks against Language Models Hongyan Chang Hamed Hassani Reza Shokri WaLM 67 3 0 19 Jul 2024
Embarrassingly Simple Text Watermarks Ryoma Sato Yuki Takezawa Han Bao Kenta Niwa Makoto Yamada WaLM 32 14 0 13 Oct 2023
Robust Distortion-free Watermarks for Language Models Rohith Kuditipudi John Thickstun Tatsunori Hashimoto Percy Liang WaLM 44 159 0 28 Jul 2023
RADAR: Robust AI-Text Detection via Adversarial Learning Xiaomeng Hu Pin-Yu Chen Tsung-Yi Ho DeLMO 52 115 0 07 Jul 2023
The Science of Detecting LLM-Generated Texts Ruixiang Tang Yu-Neng Chuang Xia Hu DeLMO 42 169 0 04 Feb 2023
Addressing Segmentation Ambiguity in Neural Linguistic Steganography Jumon Nozaki Yugo Murawaki 12 5 0 12 Nov 2022
On Information Hiding in Natural Language Systems Geetanjali Bihani Julia Taylor Rayz 23 0 0 12 Mar 2022