{"ID":6138181,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T09:33:58.260627797Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07209","arxiv_id":"2607.07209","title":"Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe","abstract":"Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interaction. Motivated by participation privacy, we study single-edit neighboring user streams, where one insertion/deletion shifts all subsequent updates and defeats standard Hamming-neighbor continual-release analyses. We give an auditable modular recipe. A randomized buffering wrapper emits bins of size $[U,2U]$, reducing single-edit streams to a Hamming-style per-bin update stream with explicit backlog/delay guarantees, where $U$ is calibrated by the privacy parameters $(\\varepsilon,δ)$. We then prove a certification theorem identifying when a non-adaptive Hamming-neighbor DP proof for a continual primitive lifts to adaptive inputs: the primitive must use fresh per-round randomness and have a stable one-round privacy profile under common adaptive context. Together, these ingredients yield trajectory-level $(\\varepsilon,δ)$-DP for single-edit streams using standard primitives (e.g., tree prefix sums), with an explicit privacy--latency link via $U$.","short_abstract":"Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interaction. Motivated by participation privacy, we study single-edit neighboring user streams, where one insertion/deletion shifts all subsequent updates and defeats standard H...","url_abs":"https://arxiv.org/abs/2607.07209","url_pdf":"https://arxiv.org/pdf/2607.07209v1","authors":"[\"T-H. Hubert Chan\",\"Elaine Shi\",\"Mengshi Zhao\",\"Mingxun Zhou\"]","published":"2026-07-08T09:44:27Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.LG\"]","methods":"[]","has_code":false}