When Global Gating Is Enough: Admission-Time Hubness Control in Anisotropic Vector Retrieval Systems

Computer Science > Cryptography and Security [Submitted on 18 Jun 2026] When Global Gating Is Enough: Admission-Time Hubness Control in Anisotropic Vector Retrieval Systems Prashant Kumar Pathak, Tarun Kumar Sharma Vector hubness, where a few points become nearest neighbors of many queries, creates a poisoning risk in retrieval-augmented generation (RAG): one injected document can influence unrelated requests. Existing defenses use periodic reverse-kNN scans, leaving an exposure window and repeated corpus-wide work. We study admission-time control, scoring each candidate against sentinel queries and quarantining hub-like documents before insertion. Across two 100,000-document corpora, five encoders, and disjoint attacker and defender query sets, a global gate achieves recall 1.0 at the decisive embedding-space point (>=0.92 across the effective range) and 0.91 +/- 0.07 on HotFlip attacks, with 1% false positives on general documents. A per-topic gate provides no reliable benefit, consistent with anisotropy coupling local and global visibility. Thresholds are maintained incrementally, with corpus-size-independent insertion cost and amortized deletion cost. On HNSW, admission adds about 3.1% to ingestion latency, scoring remains flat to 10^6 vectors, and 1.2% of decisions flip under approximate indexing, none involving attacks. Provenance complements the gate for natural or tight-domain hubs. Subjects: Cryptography and Security (cs.CR); Databases (cs.DB); Information Retrieval (cs.IR) Cite as: arXiv:2606.19692 [cs.CR]   (or arXiv:2606.19692v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.19692 Focus to learn more Submission history From: Prashant Kumar Pathak [view email] [v1] Thu, 18 Jun 2026 01:40:36 UTC (520 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.DB cs.IR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)