{"ID":5935703,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03392","arxiv_id":"2607.03392","title":"Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes","abstract":"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.","short_abstract":"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-dimensi...","url_abs":"https://arxiv.org/abs/2607.03392","url_pdf":"https://arxiv.org/pdf/2607.03392v1","authors":"[\"Gergely Flamich\",\"Oykü Sıla Güner\",\"Yanxiao Liu\",\"Deniz Gündüz\"]","published":"2026-07-03T14:49:31Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}