Solar energy paper index
SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval
One-line summary
A solar energy research paper on SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval.
Engineering notes
Engineering notes will be added by the Power for Solar editorial team.
Chinese explanation / 中文解读
中文解读待补充:本站会优先为光伏效率、钙钛矿太阳能电池、储能技术、太阳能热利用、BIPV、并网技术等高价值论文补充中文说明。
Original abstract
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. We introduce Shard, a retrieval-preserving embedding transform that removes this weak axis. The centred embedding is split into a short public prefix (for stage-1 retrieval) and a private residual sharded into C cells under separate secret keys; the residual is reranked under CKKS, where the keys cancel and leave the inner product exact. A single parameter C runs the design from the global-linear baseline it replaces (C=1) to per-document micro-keys (C=N). Because the rerank is full-dimensional, Shard returns the raw-space nDCG@10 that half-SVD truncation gives up; and because the residual is keyed cell-locally, mapping it back to a common frame under a diffuse known-plaintext leak costs roughly C times more anchors (median 200 to 102,400 at C=256), for a few encrypted queries. The short public prefix leaks far less neighbour structure, and a micro-key limit drives the residual graph to zero with an unlinkable, renewable template. The barrier holds against learned, non-linear and unsupervised aligners, and where a matched-utility noise defence de-anonymises almost every probe, Shard de-anonymises none. We are plain about the limits: within a cell the keys cancel, a targeted attacker needs only about d_priv anchors, and an overlapping reference corpus still leaks through the prefix. Shard is an attack-aware geometric defence, not a cryptographic guarantee.
Links and sources
Need this topic turned into a technical roadmap?
Power for Solar can prepare a custom solar energy literature review, simulation code map, dataset map, and B2B photovoltaic technology assessment.
Request B2B research
Comments