Watermark Smoothing Attacks against Language Models

E. J. Gumbel, “Statistical theory of extreme valuse and some practical applications,” Nat. Bur. Standards Appl. Math. Ser. 33 , 1954

1954

Earlier work this paper cites.

E. Gabrilovich and A. Gontmakher, “The homograph attack,” Communications of the ACM , vol. 45, no. 2, p. 128, 2002

2002

Earlier work this paper cites.

N. Boucher, I. Shumailov, R. Anderson, and N. Papernot, “Bad characters: Imperceptible nlp attacks,” in 2022 IEEE Symposium on Security and Privacy (SP) . IEEE, 2022, pp. 1987–2004

2004

Earlier work this paper cites.

J. N. Helfrich and R. Neff, “Dual canonicalization: An answer to the homograph attack,” in 2012 eCrime Researchers Summit . IEEE, 2012, pp. 1–10

2012

Earlier work this paper cites.

A. Fan, M. Lewis, and Y. Dauphin, “Hierarchical neural story generation,” in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2018, pp. 889–898

2018

Earlier work this paper cites.

A. Holtzman, J. Buys, M. Forbes, A. Bosselut, D. Golub, and Y. Choi, “Learning to write with cooperative discriminators,” in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2018, pp. 1638–1649

2018

Earlier work this paper cites.

A. Holtzman, J. Buys, L. Du, M. Forbes, and Y. Choi, “The curious case of neural text degeneration,” in International Conference on Learning Representations , 2019

2019

Earlier work this paper cites.

OECD, “Oecd ai principles,” Available at: https://oecd.ai/en/dashboards/ai-principles/ , 2019, guidelines for ethical, trustworthy AI. Transparency and accountability are key principles

2019

Earlier work this paper cites.

C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, “Exploring the limits of transfer learning with a unified text-to-text transformer,” Journal of machine learning research , vol. 21, no. 140, pp. 1–67, 2020

2020

Earlier work this paper cites.

T. Brown, B. Mann, N. Ryder, D. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, L. Ouyang, and D. Amodei, “Language models are few-shot learners,” Advances in Neural Information Processing Systems , 2020, seminal paper introducing GPT-3, discussing the importance of probabilities in understanding model behavior

2020

Earlier work this paper cites.

L. Pajola and M. Conti, “Fall of giants: How popular text-based mlaas fall against a simple evasion attack,” in 2021 IEEE European Symposium on Security and Privacy (EuroS&P) . IEEE, 2021, pp. 198–211

2021

Earlier work this paper cites.

European Commission, “The EU Artificial Intelligence Act,” Available at: https://artificialintelligenceact.eu/ , 2021, proposed regulation focusing on transparency and accountability in high-risk AI systems

2021

Earlier work this paper cites.

S. Zhang, S. Roller, N. Goyal, M. Artetxe, M. Chen, S. Chen, C. Dewan, M. Diab, X. Li, X. V. Lin et al. , “Opt: Open pre-trained transformer language models,” arXiv preprint arXiv:2205.01068 , 2022

Original

2022

Earlier work this paper cites.

X. L. Li, A. Holtzman, D. Fried, P. Liang, J. Eisner, T. Hashimoto, L. Zettlemoyer, and M. Lewis, “Contrastive decoding: Open-ended text generation as optimization,” arXiv preprint arXiv:2210.15097 , 2022

Original

2022

Earlier work this paper cites.

J. Wieting, K. Gimpel, G. Neubig, and T. Berg-Kirkpatrick, “Paraphrastic representations at scale,” in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations , 2022, pp. 379–388

2022

Earlier work this paper cites.

S. Aaronson, “Simons institute talk on watermarking of large language models,” https://simons.berkeley.edu/talks/scott-aaronson-ut-austin-openai-2023-08-17 , 2023

2023

Earlier work this paper cites.

M. Christ, S. Gunn, and O. Zamir, “Undetectable watermarks for language models,” arXiv preprint arXiv:2306.09194 , 2023

Original

2023

Earlier work this paper cites.

B. Huang, B. Zhu, H. Zhu, J. D. Lee, J. Jiao, and M. I. Jordan, “Towards optimal statistical watermarking,” arXiv preprint arXiv:2312.07930 , 2023

Original

2023

Cited alongside, same era.

J. Kirchenbauer, J. Geiping, Y. Wen, J. Katz, I. Miers, and T. Goldstein, “A watermark for large language models,” in Proceedings of the 40th International Conference on Machine Learning , ser. Proceedings of Machine Learning Research, A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato, and J. Scarlett, Eds., vol. 202. PMLR, 23–29 Jul 2023, pp. 17 061–17 084. [Online]. Available: https://proceedings.mlr.press/v202/kirchenbauer23a.html

2023

Cited alongside, same era.

R. Kuditipudi, J. Thickstun, T. Hashimoto, and P. Liang, “Robust distortion-free watermarks for language models,” arXiv preprint arXiv:2307.15593 , 2023

Original

2023

Cited alongside, same era.

J. Kirchenbauer, J. Geiping, Y. Wen, M. Shu, K. Saifullah, K. Kong, K. Fernando, A. Saha, M. Goldblum, and T. Goldstein, “On the reliability of watermarks for large language models,” arXiv preprint arXiv:2306.04634 , 2023

S. Dathathri, A. See, S. Ghaisas, P.-S. Huang, R. McAdam, J. Welbl, V. Bachani, A. Kaskasoli, R. Stanforth, T. Matejovicova et al. , “Scalable watermarking for identifying large language model outputs,” Nature , vol. 634, no. 8035, pp. 818–823, 2024

2024

Closest in time.

A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Yang, A. Fan et al. , “The llama 3 herd of models,” arXiv preprint arXiv:2407.21783 , 2024

Original

2024

Closest in time.

Y. Chu, J. Xu, Q. Yang, H. Wei, X. Wei, Z. Guo, Y. Leng, Y. Lv, J. He, J. Lin et al. , “Qwen2-audio technical report,” arXiv preprint arXiv:2407.10759 , 2024

Original

2024

Closest in time.

M. Christ and S. Gunn, “Pseudorandom error-correcting codes,” in Annual International Cryptology Conference . Springer, 2024, pp. 325–347

2024

Closest in time.