通过数据分布建模实现精确删忆，理论保证接近理想重训练效果。
Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning
- 基于数据分布结构推导删忆信号，不依赖参数更新。
- 在三种遗忘场景下，模型逼近理想重训练结果。
- 适合关注隐私保护与可证明安全性的研究者。
本文提出一种范式转变，将机器删忆直接关联到数据分布的结构，而非仅更新神经网络参数。我们证明，精准推断这些分布可提炼出由建模过程引发的精确删忆信号。在可验证的合理性准则下，对理想重训练模型与本方法生成的删忆模型之间KL散度的理论边界，揭示了该框架的可靠性。实验在三种遗忘场景中验证了该方法的有效性，其生成的分类器在性能上最接近理想重训练模型。
原文摘要 · Abstract (English)
This paper proposes a paradigm shift linking machine unlearning directly to the structure of the data distributions rather than a mere update of the neural network parameters. We show that inferring these distributions with precision enables distilling the exact unlearning signal induced by the modeling. Theoretical bounds on the Kullback-Leibler divergence from the ideal retrained model to our unlearned model, under verifiable admissibility criterion, reveal the soundness of our framework. This method is experimentally validated over three forgetting scenarios as reaching the closest classifier to the ideal retrained model when compared to competitors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。