Pith Number

pith:PLYUFWGV

pith:2026:PLYUFWGV3KAGFSOKLN4Y4GS6VS

not attested not anchored not stored refs resolved

Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis

Gyeongjung Kim, Haebom Lee

A keyed nonlinear transform applied to split-inference features cuts re-identification AUC from 0.635 to 0.586 with 0.15 ms overhead and no backbone retraining.

arxiv:2605.14123 v1 · 2026-05-13 · eess.IV · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PLYUFWGV3KAGFSOKLN4Y4GS6VS}

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

KNT reduces re-identification AUC from 0.635 to 0.586, corresponding to a 36% reduction in above-chance identity signal, while introducing only 0.15 ms CPU overhead, without backbone retraining, and preserving classification performance within 1.0 pp.

C2weakest assumption

The assumption that the secret key stays secure and that the nonlinear transform forces any inversion attempt into iterative gradient-based optimization even under full key compromise.

C3one line summary

KNT applies key-conditioned nonlinear obfuscation to split-inference features, cutting re-identification AUC from 0.635 to 0.586 with 0.15 ms overhead and under 1 pp accuracy loss.

References

27 extracted · 27 resolved · 2 Pith anchors

[1] Brendan and Mironov, Ilya and Talwar, Kunal and Zhang, Li , year= 2016 · doi:10.1145/2976749.2978318

[2] Privacy-preserving collaborative medical image segmentation using la- tent transform networks.arXiv preprint arXiv:2603.05541, 2026 2026

[3] Is pri- vate learning possible with instance encoding? InProceedings of the 2021 IEEE Sym- posium on Security and Privacy (S&P), pages 410–427 2021

[4] Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic) 2018 · arXiv:1902.03368

[5] URLhttps://doi.org/10.1561/ 0400000042 2014 · doi:10.1561/0400000042

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:11.876838Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7af142d8d5da8062c9ca5b798e1a5eacb77dff68fbadddfb73d7aa3b8c6f2cd5

Aliases

arxiv: 2605.14123 · arxiv_version: 2605.14123v1 · doi: 10.48550/arxiv.2605.14123 · pith_short_12: PLYUFWGV3KAG · pith_short_16: PLYUFWGV3KAGFSOK · pith_short_8: PLYUFWGV

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/PLYUFWGV3KAGFSOKLN4Y4GS6VS \
  | 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: 7af142d8d5da8062c9ca5b798e1a5eacb77dff68fbadddfb73d7aa3b8c6f2cd5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bedd8d778f5e51f43d74ddf6ea8456a63749a5932b3b9cfb6a9342775a4162c7",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "eess.IV",
    "submitted_at": "2026-05-13T21:17:41Z",
    "title_canon_sha256": "6230f551fa8af1782191d686c19d1a3a12311a5562c3c76f223dbb92c32bc3c1"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14123",
    "kind": "arxiv",
    "version": 1
  }
}