Pith Number

pith:YEM54AE6

pith:2026:YEM54AE6TCCLSFT4H3AXUFNHVS

not attested not anchored not stored refs pending

Dual-branch Robust Unlearnable Examples

Changsong Jiang, Hangtao Zhang, Li Zeng, Wenbo Pan, Xianlong Wang, Xiaohua Jia, Ziqi Zhou

DUNE achieves robust unlearnability by separately optimizing perturbations in spatial and color domains.

arxiv:2605.01718 v2 · 2026-05-03 · 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{YEM54AE6TCCLSFT4H3AXUFNHVS}

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

DUNE separately optimizes perturbations in the spatial and color domains to establish the mapping between perturbations and shift-induced labels... DUNE's robustness outperforms 12 SOTA UE schemes under 7 mainstream defenses, yielding a lower average test accuracy of 14.95% to 50.82%.

C2weakest assumption

That dual-branch optimization in spatial and color domains combined with ensemble aggregation will reliably increase noise intensity, drive models to learn perturbation-oriented features, and maintain unlearnability against advanced defenses without introducing exploitable weaknesses.

C3one line summary

DUNE creates robust unlearnable examples through dual-branch spatial-color perturbation optimization and ensemble strategies, achieving lower average test accuracies of 14.95% to 50.82% than 12 prior methods against 7 defenses on CIFAR-10 and ImageNet.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics

Receipt and verification

First computed	2026-06-29T01:14:32.664231Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c119de009e9884b9167c3ec17a15a7aca98237a2b57427ddddbb6fad07c266e7

Aliases

arxiv: 2605.01718 · arxiv_version: 2605.01718v2 · doi: 10.48550/arxiv.2605.01718 · pith_short_12: YEM54AE6TCCL · pith_short_16: YEM54AE6TCCLSFT4 · pith_short_8: YEM54AE6

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/YEM54AE6TCCLSFT4H3AXUFNHVS \
  | 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: c119de009e9884b9167c3ec17a15a7aca98237a2b57427ddddbb6fad07c266e7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2717284d8b63be9c3a8cb78e96ce258203aaf12ba5b58065dc4d188369de3d5c",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-03T05:19:21Z",
    "title_canon_sha256": "a3eafba55ab20e3761e1ef2ed46c41dc642e0517f5d495928fe641883887d107"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.01718",
    "kind": "arxiv",
    "version": 2
  }
}