REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models. Zhang, R., Hussain, S. S., Neekhara, P., & Koushanfar, F. In Balzarotti, D. & Xu, W., editors, 33rd USENIX Security Symposium, USENIX Security 2024, Philadelphia, PA, USA, August 14-16, 2024, 2024. USENIX Association.
REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models [link]Paper  bibtex   2 downloads  
@inproceedings{DBLP:conf/uss/ZhangHNK24,
  author       = {Ruisi Zhang and
                  Shehzeen Samarah Hussain and
                  Paarth Neekhara and
                  Farinaz Koushanfar},
  editor       = {Davide Balzarotti and
                  Wenyuan Xu},
  title        = {{REMARK-LLM:} {A} Robust and Efficient Watermarking Framework for
                  Generative Large Language Models},
  booktitle    = {33rd {USENIX} Security Symposium, {USENIX} Security 2024, Philadelphia,
                  PA, USA, August 14-16, 2024},
  publisher    = {{USENIX} Association},
  year         = {2024},
  url          = {https://drive.google.com/uc?export=download&id=1fB4wRre-S9tom-hcmopCBsZbJZ50E7Bn},
  timestamp    = {Mon, 22 Jul 2024 17:10:49 +0200},
  biburl       = {https://dblp.org/rec/conf/uss/ZhangHNK24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 2