用扩散模型与随机编码实现高维数据的隐私压缩，兼顾压缩率与隐私安全。
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
- 结合扩散模型与随机编码，构建可调控压缩率-隐私-效用平衡的压缩管道。
- 在CIFAR-10上实现10至30倍的压缩提升，隐私与图像质量保持不变。
- 适用于需高效存储或传输敏感图像数据的场景，如医疗影像共享。
个人数据的持续增长带来了保护个体身份敏感信息的巨大压力。差分隐私（DP）提供了具有严格形式保障的可靠框架，并已取得实际成功。然而，释放高维数据（如图像）仍面临挑战：未压缩的私有化数据需要大量存储空间。同时，尚无有效的数据压缩方案能在隐私保障下压缩高分辨率数据。我们提出DP-DiPP，一种融合随机编码与扩散模型的压缩流程。该方法高度灵活，使用者可直接控制压缩率-隐私-效用之间的权衡。理论基础上，我们将泊松私有表示（PPR）扩展至编码隐私机制输出。随后将其与基于扩散的有损压缩方法DiffC结合，构建出一种差分隐私图像压缩器。在CIFAR-10上的隐私图像分类实验表明，与基线相比，DP-DiPP显著优于现有方法，在保持相当隐私保证和实用性的同时，实现了10至30倍的压缩率提升。
原文摘要 · Abstract (English)
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.
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。