提出可证明的神经网络删训方法，确保数据删除后模型不再依赖该数据。
Certified Unlearning for Neural Networks
- 通过在保留数据上加噪微调，实现可证明的删训保证。
- 无需对损失函数做假设，适用于多种模型和场景。
- 兼顾理论严谨性与实际性能，适合隐私敏感应用。
我们研究机器删训问题，目标是应请求移除特定训练数据对模型的影响，以应对隐私担忧和如“被遗忘权”等法规要求。现有方法依赖于严格假设或缺乏正式保障。为此，我们提出一种新型可证明的机器删训方法，利用删训与随机后处理下的隐私放大之间的联系。该方法通过对需保留的数据进行加噪微调，确保可证明的删训效果，且无需对底层损失函数做任何假设，具有广泛的适用性。我们分析了效率与准确率之间的理论权衡，并通过实验证明该方法不仅具备正式的删训保障，而且在实际中表现优异，优于现有基线。代码已公开于 https://github.com/stair-lab/certified-unlearning-neural-networks-icml-2025。
原文摘要 · Abstract (English)
We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten." Unfortunately, existing methods rely on restrictive assumptions or lack formal guarantees. To this end, we propose a novel method for certified machine unlearning, leveraging the connection between unlearning and privacy amplification by stochastic post-processing. Our method uses noisy fine-tuning on the retain data, i.e., data that does not need to be removed, to ensure provable unlearning guarantees. This approach requires no assumptions about the underlying loss function, making it broadly applicable across diverse settings. We analyze the theoretical trade-offs in efficiency and accuracy and demonstrate empirically that our method not only achieves formal unlearning guarantees but also performs effectively in practice, outperforming existing baselines. Our code is available at https://github.com/stair-lab/certified-unlearning-neural-networks-icml-2025
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。