Pith Number

pith:N3G3EZNR

pith:2026:N3G3EZNRVLBLMHBXWSKVELZV2R

not attested not anchored not stored refs pending

Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects

Hanxi Li, Jiale Lao, Jianan Zhou, Junfen Wang, Mingjie Tang, Yang Cao, Yibo Wang, Zhengmao Ye

A few vectors placed near the center of an embedding space can appear in the top results for nearly every query.

arxiv:2604.05480 v2 · 2026-04-07 · cs.CR · cs.DB

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{N3G3EZNRVLBLMHBXWSKVELZV2R}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The attack shows that vectors in a vector database cannot be blindly trusted: geometric defects in high-dimensional embeddings make retrieval inherently vulnerable.

C2weakest 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.

C3one 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.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems

Receipt and verification

First computed	2026-07-02T01:17:30.610397Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6ecdb265b1aac2b61c37b495522f35d45044ce252c113084800e68258e5e57f6

Aliases

arxiv: 2604.05480 · arxiv_version: 2604.05480v2 · doi: 10.48550/arxiv.2604.05480 · pith_short_12: N3G3EZNRVLBL · pith_short_16: N3G3EZNRVLBLMHBX · pith_short_8: N3G3EZNR

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/N3G3EZNRVLBLMHBXWSKVELZV2R \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 6ecdb265b1aac2b61c37b495522f35d45044ce252c113084800e68258e5e57f6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2a7a583d1f1c7c0a98c4f2e1e4421f1d171dc74cf2a0a1dc8d81e5290d6e2e3f",
    "cross_cats_sorted": [
      "cs.DB"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-04-07T06:21:41Z",
    "title_canon_sha256": "f8943bab60bd349417d682573558bdc2c2e532ab8b330df55e0b5e2e665fa838"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.05480",
    "kind": "arxiv",
    "version": 2
  }
}