{"paper":{"title":"SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CR","authors_text":"Sergey Kurilenko","submitted_at":"2026-06-26T11:26:53Z","abstract_excerpt":"Dense embeddings underpin semantic search and RAG, yet a leaked vector store hands much of the underlying text back to whoever holds it. The attacks that make this possible (few-shot alignment, zero-shot inversion, unsupervised cross-space translation) share one weakness: the protected store is a single global geometry that can be aligned to a known one. A secret global rotation, the usual lightweight defence, is no exception: orthogonal Procrustes recovers it once the attacker has about the subspace dimension in known pairs.\n  We introduce Shard, a retrieval-preserving embedding transform tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27976","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.27976/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}