arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.03392cs.CRcs.LG
收藏

通过扩散和随机码实现可扩展的差分隐私数据压缩

Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes

Imperial College London(帝国理工学院)

Gergely Flamich, Oykü Sıla Güner, Yanxiao Liu, Deniz Gündüz

AI总结:

针对高维数据压缩难题,提出结合随机码与扩散模型的DP-DiPP压缩管道,通过扩展泊松私有表示并结合DiffC,实现差分隐私图像压缩,实验表明其性能远超基线。

摘要:

个人数据收集增加,需保护隐私技术。差分隐私有形式化保障但高维数据压缩难。本文提出DP-DiPP,结合随机码与扩散模型,高度灵活。扩展泊松私有表示编码隐私机制输出,与DiffC结合得差分隐私图像压缩器,实验显示其性能远超基线。

英文摘要:

The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual identity. Differential privacy (DP) provides a principled framework with strong formal guarantees and has already achieved practical success. However, releasing high-dimensional data, such as images, has remained elusive: releasing uncompressed privatized data requires significant storage. At the same time, no effective data compression scheme exists that can compress high-resolution data with privacy guarantees. We address this challenge with DP-DiPP, a compression pipeline that combines stochastic codes with diffusion models. DP-DiPP is highly flexible: the practitioner has direct control over the compression rate-privacy-utility tradeoff. As the theoretical backbone, we extend the Poisson private representation (PPR) to encode the outputs of privacy mechanisms. We then combine it with DiffC, a diffusion-based lossy data compression method, to obtain a differentially private image compressor. Our experiments on privatized image classification on CIFAR-10 demonstrate that DP-DiPP significantly outperforms the baseline, achieving a 10-30 times better compression while retaining comparable privacy guarantees and utility.

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。

↑