Pith Number

pith:L66OCX2V

pith:2026:L66OCX2VMFITANOO7VUXRY7J76

not attested not anchored not stored refs resolved

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation

Jiancheng Shi, Lilin Zhang, Xianggen Liu, Yimo Guo, Yue Li

Adaptive perturbations can rebalance class distributions during adversarial training

arxiv:2605.13395 v1 · 2026-05-13 · cs.LG · 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{L66OCX2VMFITANOO7VUXRY7J76}

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

perturbations can simultaneously address both adversarial vulnerability and class imbalance. Based on these insights, we propose RobustLT, a plug-and-play framework that adaptively adjusts perturbations during adversarial training. Extensive experiments demonstrate that RobustLT consistently enhances adversarial robustness and class-balance on long-tailed datasets.

C2weakest assumption

The theoretical claim that perturbations inherently alter the training distribution in a way that simultaneously fixes both skew and instability holds without introducing new instabilities or requiring dataset-specific tuning beyond the adaptive rule.

C3one line summary

RobustLT adaptively adjusts perturbations in adversarial training to simultaneously improve robustness and class balance on long-tailed datasets.

References

53 extracted · 53 resolved · 2 Pith anchors

[1] Recent advances in adversarial training for adversarial ro- bustness 2021

[2] Evasion attacks against machine learning at test time 2013

[3] A systematic study of the class imbalance problem in convolu- tional neural networks.Neural Networks, 106:249–259, 2018 2018

[4] A unified wasserstein distributional robustness framework for adversarial training 2022

[5] Learning imbalanced datasets with label- distribution-aware margin loss.Advances in Neural Informa- tion Processing Systems, 32, 2019 2019

Receipt and verification

First computed	2026-05-18T02:44:47.666009Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5fbce15f5561513035cefd6978e3e9ffb81660fc3fe2b964af37e5836f5ff2b6

Aliases

arxiv: 2605.13395 · arxiv_version: 2605.13395v1 · doi: 10.48550/arxiv.2605.13395 · pith_short_12: L66OCX2VMFIT · pith_short_16: L66OCX2VMFITANOO · pith_short_8: L66OCX2V

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/L66OCX2VMFITANOO7VUXRY7J76 \
  | 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: 5fbce15f5561513035cefd6978e3e9ffb81660fc3fe2b964af37e5836f5ff2b6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "feb1200c667e62499a964fa0350b9855e7bae6f42b91582fecb2e441b879e76a",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T11:51:46Z",
    "title_canon_sha256": "81bea3319b199b02d255251cd202e5accab761dfd22b0d4d2c4bb7980e3ac8a9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13395",
    "kind": "arxiv",
    "version": 1
  }
}