Author : James Scheibner, Jean Louis Raisaro, Juan Ramón Troncoso-Pastoriza, Marcello Ienca, Jacques Fellay, Effy Vayena, Jean-Pierre Hubaux

Paper Link:  https://www.jmir.org/2021/2/e25120/

참고

• Extracting Training Data from Large Language Models (Nicholas Carlini et al., USENIX Security 21)
• Extracting Training Data from Diffusion Models (Nicholas Carlini et al., Arxiv 2023)

• Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy (Darphne Ippolito, Arxiv 2023)