---
title: "DP-DiPP：基于扩散与随机码的可扩展差分隐私数据压缩"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.03392v1"
permalink: "https://feed.astralor.com/items/itm_f9db5669d57bc37d413cb6c5"
published: "2026-07-03T14:49:31.000Z"
score: 79
channel: "ai"
tags: ["DP-DiPP","差分隐私","扩散模型","数据压缩","泊松隐私表示","随机码"]
---

# DP-DiPP：基于扩散与随机码的可扩展差分隐私数据压缩

## AI 点评

> 这篇论文最值得关注的是它首次将扩散模型的生成能力与随机码的隐私特性巧妙融合，实现了10倍以上的压缩率提升。对从事隐私计算、数据压缩和图像处理的AI研究员与工程师而言，DP-DiPP提供了一个可直接参考的框架，有望解决真实场景中高维隐私数据存储与传输的瓶颈。

## 速览

本文提出DP-DiPP，一种结合扩散模型与随机码的差分隐私数据压缩流水线，解决了高维图像数据在隐私保护下难以高效压缩的难题。该方案允许用户直接控制压缩率-隐私-效用三者的权衡，理论层面将泊松隐私表示（PPR）扩展用于编码隐私机制的输出，并结合DiffC扩散压缩方法。在CIFAR-10上的实验表明，相比基线，DP-DiPP实现了10-30倍的更好压缩比，同时保持相当的隐私保证和效用。

## 关键点

- 提出DP-DiPP，首个将扩散模型与随机码结合的差分隐私图像压缩方案。
- 扩展泊松隐私表示（PPR）以编码隐私机制输出，提供理论保证。
- 在CIFAR-10图像分类任务上，相比基线提升10-30倍压缩率。
- 用户可灵活调节压缩率-隐私-效用的权衡。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_f9db5669d57bc37d413cb6c5