Skip to yearly menu bar Skip to main content


Poster
in
Workshop: 2nd Workshop on Generative AI and Law (GenLaw ’24)

Randomization Techniques to Mitigate the Risk of Copyright Infringement

Wei-Ning Chen · Peter Kairouz · Sewoong Oh · Zheng Xu


Abstract:

In this work, we address the challenges in the Near Access Freeness (NAF) framework for copyright protection. We propose a Monte Carlo estimator to empirically measure the NAF bounds and conduct experiments to compare NAF-based solutions with differential privacy (DP)-based solutions, which impose stricter constraints. Finally, we introduce additional randomization techniques to enhance model ensemble methods, such as CP-(\Delta) and CP-(k).

Chat is not available.