Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model (opens in new tab)

Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector: when a vector database leaks, the documents behind it leak too. The textbook defences are extremes - encrypting the whole search homomorphically is sound but too slow at million-document scale, while privacy noise degrades ranking long before it protects. We study a middle path exploiting the asy...