Fetching the paper…
Reading the bibliography…
We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone.
The curious case of neural text degeneration
Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi · 1904
Earlier work this paper cites.
GLTR: Statistical detection and visualization of generated text
Sebastian Gehrmann, Hendrik Strobelt, and Alexander M Rush · 1906
Earlier work this paper cites.
Random oracles are practical: A paradigm for designing efficient protocols
Mihir Bellare and Phillip Rogaway · 1993
Earlier work this paper cites.
Probability inequalities for sums of bounded random variables
Wassily Hoeffding · 1994
Earlier work this paper cites.
An information-theoretic model for steganography
Christian Cachin · 1998
Earlier work this paper cites.
Short signatures from the Weil pairing
Dan Boneh, Ben Lynn, and Hovav Shacham · 2001
Earlier work this paper cites.
Secret and public key image watermarking schemes for image authentication and ownership verification
Ping Wah Wong and Nasir Memon · 2001
Earlier work this paper cites.
Provably secure steganography
Nicholas J Hopper, John Langford, and Luis Von Ahn · 2002
Earlier work this paper cites.
A secure and robust digital signature scheme for JPEG2000 image authentication
Qibin Sun and Shih-Fu Chang · 2005
Earlier work this paper cites.
Detecting fake content with relative entropy scoring
Thomas Lavergne, Tanguy Urvoy, and François Yvon · 2008
Earlier work this paper cites.
Automatic detection of machine generated text: A critical survey
Ganesh Jawahar, Muhammad Abdul-Mageed, and Laks VS Lakshmanan · 2011
Earlier work this paper cites.
Computer-generated text detection using machine learning: A systematic review
Daria Beresneva · 2016
Earlier work this paper cites.
Deletion codes in the high-noise and high-rate regimes
Venkatesan Guruswami and Carol Wang · 2017
Earlier work this paper cites.
PyTorch: An imperative style, high-performance deep learning library
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al · 2019
Earlier work this paper cites.
Neural text generation with unlikelihood training
Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, and Jason Weston · 2019
Earlier work this paper cites.
Defending against neural fake news
Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi · 2019
Earlier work this paper cites.
Exploring the limits of transfer learning with a unified text-to-text transformer
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu · 2020
Cited alongside, same era.
Adversarial watermarking transformer: Towards tracing text provenance with data hiding
Sahar Abdelnabi and Mario Fritz · 2021
Cited alongside, same era.
Meteor: Cryptographically secure steganography for realistic distributions
Gabriel Kaptchuk, Tushar M Jois, Matthew Green, and Aviel D Rubin · 2021
Cited alongside, same era.
Rejection sampling revisit: how to choose parameters in lattice-based signature
Zhongxiang Zheng, Anyu Wang, and Lingyue Qin · 2021
Cited alongside, same era.
Don’t reject this: Key-recovery timing attacks due to rejection-sampling in HQC and BIKE
Qian Guo, Clemens Hlauschek, Thomas Johansson, Norman Lahr, Alexander Nilsson, and Robin Leander Schröder · 2022
Cited alongside, same era.
A private watermark for large language models
Aiwei Liu, Leyi Pan, Xuming Hu, Shu’ang Li, Lijie Wen, Irwin King, and Philip S Yu · 2023
Closest in time.
DetectGPT: zero-shot machine-generated text detection using probability curvature
Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D. Manning, and Chelsea Finn · 2023
Closest in time.
OpenAI · 2023
Closest in time.
Mark my words: Analyzing and evaluating language model watermarks
Julien Piet, Chawin Sitawarin, Vivian Fang, Norman Mu, and David Wagner · 2023
Closest in time.
Natural language watermarking via paraphraser-based lexical substitution
Jipeng Qiang, Shiyu Zhu, Yun Li, Yi Zhu, Yunhao Yuan, and Xindong Wu · 2023
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
High-resolution image synthesis with latent diffusion models
Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer · 2022
Cited alongside, same era.
Opt: Open pre-trained transformer language models
Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al · 2022
Cited alongside, same era.
Neurocryptography
Scott Aaronson · 2023
Cited alongside, same era.
On the possibilities of AI-generated text detection
Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, and Furong Huang · 2023
Cited alongside, same era.
Yi Chen, Rui Wang, Haiyun Jiang, Shuming Shi, and Ruifeng Xu · 2023
Cited alongside, same era.
Hugging face transformers
Hugging Face · 2023
Cited alongside, same era.
GPTZero — The Trusted AI Detector for ChatGPT, GPT-4, & More
GPTZero · 2023
Cited alongside, same era.
Can AI-generated text be reliably detected?
Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, and Soheil Feizi · 2023
Closest in time.
Llama 2: Open foundation and fine-tuned chat models
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al · 2023
Closest in time.
Robust natural language watermarking through invariant features
KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, and Nojun Kwak · 2023
Closest in time.
Undetectable watermarks for language models
Miranda Christ, Sam Gunn, and Or Zamir · 2024
Closest in time.
Edit distance robust watermarks for language models
Noah Golowich and Ankur Moitra · 2024
Closest in time.
Our next-generation model: Gemini 1.5
Google DeepMind · 2024
Closest in time.
Robust distortion-free watermarks for language models
Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, and Percy Liang · 2024
Closest in time.
DeepTextMark: A Deep learning-driven text watermarking approach for identifying large language model generated text
Travis Munyer, Abdullah All Tanvir, Arjon Das, and Xin Zhong · 2024
Closest in time.
Provably robust multi-bit watermarking for AI-generated text via error correction code
Wenjie Qu, Dong Yin, Zixin He, Wei Zou, Tianyang Tao, Jinyuan Jia, and Jiaheng Zhang · 2024
Closest in time.
Watermarks in the sand: Impossibility of strong watermarking for language models
Hanlin Zhang, Benjamin L. Edelman, Danilo Francati, Daniele Venturi, Giuseppe Ateniese, and Boaz Barak · 2024
Closest in time.