隐私放大在无限合成数据发布下仍持续
Privacy Amplification Persists under Unlimited Synthetic Data Release
AI总结：
本文在参数有界假设下证明了即使发布无限数量的合成数据，隐私放大仍持续，改进了之前关于线性生成器的隐私保证界限。
摘要：
我们研究了通过发布合成数据实现的隐私放大现象，这是一种在仅发布合成数据而不是私有生成模型本身时，差分隐私保证得到改善的现象。Pierquin等人（2025）最近的工作建立了线性生成器的第一个正式放大保证，但这些保证仅适用于渐近性 regime，其中模型维度远超过发布的合成记录数量，限制了其实际相关性。在本工作中，我们展示了令人惊讶的结果：在参数有界假设下，即使发布无限数量的合成记录，隐私放大仍持续存在，从而改进了Pierquin等人（2025）的界限。我们的分析提供了结构见解，可能指导更复杂的发布机制的更紧隐私保证的发展。
英文摘要：
We study privacy amplification by synthetic data release, a phenomenon in which differential privacy guarantees are improved by releasing only synthetic data rather than the private generative model itself. Recent work by Pierquin et al. (2025) established the first formal amplification guarantees for a linear generator, but they apply only in asymptotic regimes where the model dimension far exceeds the number of released synthetic records, limiting their practical relevance. In this work, we show a surprising result: under a bounded-parameter assumption, privacy amplification persists even when releasing an unbounded number of synthetic records, thereby improving upon the bounds of Pierquin et al. (2025). Our analysis provides structural insights that may guide the development of tighter privacy guarantees for more complex release mechanisms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
