Pith Number

pith:PVEIWKIR

pith:2026:PVEIWKIRQWTAXX7TKNFD6PEUPP

not attested not anchored not stored refs resolved

Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy

Anil Anthony Bharath, Viktor Schlegel, Yidan Sun, Youngmok Ha

Jacobian-guided reshaping turns isotropic LDP noise anisotropic to raise representation utility while holding the per-dimension privacy budget fixed.

arxiv:2605.16812 v1 · 2026-05-16 · cs.LG · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PVEIWKIRQWTAXX7TKNFD6PEUPP}

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

Integrating our approach improves the utility of PrivUnit2 and PrivUnitG by approximately 20% at ε=7.5 on CIFAR-10-C (Brightness corruption at severity level 5) while preserving the uniform per-dimension privacy budget.

C2weakest assumption

The Jacobian matrix of the public downstream model accurately identifies task-critical subspaces without introducing additional privacy leakage or requiring knowledge unavailable under the LDP threat model (abstract, section on method).

C3one line summary

Jacobian-guided anisotropic noise reshaping improves LDP utility by ~20% on CIFAR-10-C at ε=7.5 by attenuating noise in task-critical subspaces identified via the downstream model's Jacobian.

References

78 extracted · 78 resolved · 1 Pith anchors

[1] Theory of Cryptography Conference (TCC) , pages = 2006

[2] SIAM Journal on Computing , volume =

[3] Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS) , pages =

[4] Advances in Neural Information Processing Systems (NIPS) , pages =

[5] ICML Workshop on Federated Learning and Analytics in Practice , year =

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:23.629146Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7d488b291185a60bdff3534a3f3c947be02472e26e598e3ee13a67557e5f5e97

Aliases

arxiv: 2605.16812 · arxiv_version: 2605.16812v1 · doi: 10.48550/arxiv.2605.16812 · pith_short_12: PVEIWKIRQWTA · pith_short_16: PVEIWKIRQWTAXX7T · pith_short_8: PVEIWKIR

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/PVEIWKIRQWTAXX7TKNFD6PEUPP \
  | 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: 7d488b291185a60bdff3534a3f3c947be02472e26e598e3ee13a67557e5f5e97

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "291c8e1f3a91ffa20b1e60d28ad9b65251f6085c6a65f6df4b925eee9cee5383",
    "cross_cats_sorted": [
      "cs.CR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T05:01:41Z",
    "title_canon_sha256": "d9ce1b94ea34d8efb82df9ea98d3339f7ddf94afd2917e3ce6c5bcc7df056b48"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16812",
    "kind": "arxiv",
    "version": 1
  }
}