BriefGPT.xyz
Dec, 2023
层级攻击遗忘:通过层级攻击和知识蒸馏实现快速准确的机器遗忘
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation
HTML
PDF
Hyunjune Kim, Sangyong Lee, Simon S. Woo
TL;DR
该研究提出了一种在机器学习中,通过层攻击遗忘和知识蒸馏来解决训练集中的个人数据隐私问题的快速机器遗忘范式,通过大量实验证明了该方法在准确性和全链路遗忘性能上的有效性。
Abstract
Recently, serious concerns have been raised about the
privacy issues
related to
training datasets
in machine learning algorithms when including personal data. Various regulations in different countries, including
→