{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N3G3EZNRVLBLMHBXWSKVELZV2R","short_pith_number":"pith:N3G3EZNR","schema_version":"1.0","canonical_sha256":"6ecdb265b1aac2b61c37b495522f35d45044ce252c113084800e68258e5e57f6","source":{"kind":"arxiv","id":"2604.05480","version":2},"attestation_state":"computed","paper":{"title":"Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A few vectors placed near the center of an embedding space can appear in the top results for nearly every query.","cross_cats":["cs.DB"],"primary_cat":"cs.CR","authors_text":"Hanxi Li, Jiale Lao, Jianan Zhou, Junfen Wang, Mingjie Tang, Yang Cao, Yibo Wang, Zhengmao Ye","submitted_at":"2026-04-07T06:21:41Z","abstract_excerpt":"Vector databases serve as the retrieval backbone of modern AI applications, yet their security remains largely unexplored. We propose the Black-Hole Attack, a poisoning attack that injects a small number of malicious vectors near the geometric center of the stored vectors. These injected vectors attract queries like a black hole and frequently appear in the top-k retrieval results for most queries. This attack is enabled by a phenomenon we term centrality-driven hubness: in high-dimensional embedding spaces, vectors near the centroid become nearest neighbors of a disproportionately large numbe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2604.05480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-04-07T06:21:41Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"f8943bab60bd349417d682573558bdc2c2e532ab8b330df55e0b5e2e665fa838","abstract_canon_sha256":"2a7a583d1f1c7c0a98c4f2e1e4421f1d171dc74cf2a0a1dc8d81e5290d6e2e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:30.610950Z","signature_b64":"6EKzQITka3JFY46HqAWy+fKfSIjhH0ayhYHr49lPo0ScrSGgRnP1USGgd+z7OqaSjKU0QkX0STm/pqmah2WGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ecdb265b1aac2b61c37b495522f35d45044ce252c113084800e68258e5e57f6","last_reissued_at":"2026-07-02T01:17:30.610397Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:30.610397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A few vectors placed near the center of an embedding space can appear in the top results for nearly every query.","cross_cats":["cs.DB"],"primary_cat":"cs.CR","authors_text":"Hanxi Li, Jiale Lao, Jianan Zhou, Junfen Wang, Mingjie Tang, Yang Cao, Yibo Wang, Zhengmao Ye","submitted_at":"2026-04-07T06:21:41Z","abstract_excerpt":"Vector databases serve as the retrieval backbone of modern AI applications, yet their security remains largely unexplored. We propose the Black-Hole Attack, a poisoning attack that injects a small number of malicious vectors near the geometric center of the stored vectors. These injected vectors attract queries like a black hole and frequently appear in the top-k retrieval results for most queries. This attack is enabled by a phenomenon we term centrality-driven hubness: in high-dimensional embedding spaces, vectors near the centroid become nearest neighbors of a disproportionately large numbe"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The attack shows that vectors in a vector database cannot be blindly trusted: geometric defects in high-dimensional embeddings make retrieval inherently vulnerable.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That high-dimensional embedding spaces in practice have a nearly empty centroid region where vectors exhibit centrality-driven hubness and become nearest neighbors to a disproportionately large number of other vectors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A few vectors placed near the center of an embedding space can appear in the top results for nearly every query.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"340bab1b91fa54ed0907cad9dc5be03dea3fc271ee27860589cf41eca85d5360"},"source":{"id":"2604.05480","kind":"arxiv","version":2},"verdict":{"id":"73851eac-de30-472d-a9c3-ecd9f2879151","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:35:12.492863Z","strongest_claim":"The attack shows that vectors in a vector database cannot be blindly trusted: geometric defects in high-dimensional embeddings make retrieval inherently vulnerable.","one_line_summary":"Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That high-dimensional embedding spaces in practice have a nearly empty centroid region where vectors exhibit centrality-driven hubness and become nearest neighbors to a disproportionately large number of other vectors.","pith_extraction_headline":"A few vectors placed near the center of an embedding space can appear in the top results for nearly every query."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.05480/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":2,"snapshot_sha256":"2b8d652bc255afd8571e9dcd246bc365e6006f5a5b408c3cea35aaa8018220ac"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.05480","created_at":"2026-07-02T01:17:30.610457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.05480v2","created_at":"2026-07-02T01:17:30.610457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05480","created_at":"2026-07-02T01:17:30.610457+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3G3EZNRVLBL","created_at":"2026-07-02T01:17:30.610457+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3G3EZNRVLBLMHBX","created_at":"2026-07-02T01:17:30.610457+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3G3EZNR","created_at":"2026-07-02T01:17:30.610457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.08661","citing_title":"Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R","json":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R.json","graph_json":"https://pith.science/api/pith-number/N3G3EZNRVLBLMHBXWSKVELZV2R/graph.json","events_json":"https://pith.science/api/pith-number/N3G3EZNRVLBLMHBXWSKVELZV2R/events.json","paper":"https://pith.science/paper/N3G3EZNR"},"agent_actions":{"view_html":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R","download_json":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R.json","view_paper":"https://pith.science/paper/N3G3EZNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.05480&json=true","fetch_graph":"https://pith.science/api/pith-number/N3G3EZNRVLBLMHBXWSKVELZV2R/graph.json","fetch_events":"https://pith.science/api/pith-number/N3G3EZNRVLBLMHBXWSKVELZV2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R/action/storage_attestation","attest_author":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R/action/author_attestation","sign_citation":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R/action/citation_signature","submit_replication":"https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R/action/replication_record"}},"created_at":"2026-07-02T01:17:30.610457+00:00","updated_at":"2026-07-02T01:17:30.610457+00:00"}