pith. sign in
Pith Number

pith:7JCXNMW6

pith:2026:7JCXNMW6V3J23RMAC4GIFTU5PA
not attested not anchored not stored refs resolved

MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data

Deval Pandya, Gauri Sharma, John Jewell, Mahshid Alinoori, Masoumeh Shafieinejad, Sana Ayromlou, Veronica Chatrath, Wei Pang, Xi He

The MIDST challenge shows that membership inference attacks can quantify privacy leakage in synthetic tabular data from diffusion models.

arxiv:2603.19185 v2 · 2026-03-19 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{7JCXNMW6V3J23RMAC4GIFTU5PA}

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

MIDST inspired the development of novel black-box and white-box MIAs tailored to these target diffusion models as a key outcome, enabling a comprehensive evaluation of their privacy efficacy.

C2weakest assumption

That the synthetic tabular data generated by diffusion models can be meaningfully targeted by membership inference attacks in ways that quantify real privacy leakage, an assumption the challenge is designed to test but not independently verified in the abstract.

C3one line summary

The MIDST challenge evaluated privacy resilience of diffusion-generated synthetic tabular data via membership inference attacks and produced new black-box and white-box attack methods.

References

30 extracted · 30 resolved · 0 Pith anchors

[1] S. A. Assefa, D. Dervovic, M. Mahfouz, R. E. Tillman, P. Reddy, and M. Veloso. Generating synthetic data in finance: opportunities, challenges and pitfalls. In Proceedings of the First ACM Internation 2020
[2] P. Berka et al. Guide to the financial data set.PKDD2000 discovery challenge, 2000 2000
[3] N. Carlini, J. Hayes, M. Nasr, M. Jagielski, V . Sehwag, F. Tram `er, B. Balle, D. Ippolito, and E. Wallace. Ex- tracting training data from diffusion models. InUSENIX Security 23, pages 5253–5270, 20 2023
[4] J. Duan, F. Kong, S. Wang, X. Shi, and K. Xu. Are diffusion models vulnerable to membership inference attacks? InICML, 2023 2023
[5] J. Fonseca and F. Bacao. Tabular and latent space synthetic data generation: a literature review.Journal of Big Data, 10(1):115, 2023 2023

Cited by

2 papers in Pith

Receipt and verification
First computed 2026-05-18T02:44:30.811804Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

fa4576b2deaed3adc580170c82ce9d780dc4346666853af469de370ef88b8509

Aliases

arxiv: 2603.19185 · arxiv_version: 2603.19185v2 · doi: 10.48550/arxiv.2603.19185 · pith_short_12: 7JCXNMW6V3J2 · pith_short_16: 7JCXNMW6V3J23RMA · pith_short_8: 7JCXNMW6
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/7JCXNMW6V3J23RMAC4GIFTU5PA \
  | 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: fa4576b2deaed3adc580170c82ce9d780dc4346666853af469de370ef88b8509
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "2a59df67fe3a4bdf77f1c1ea31d7364dfdc960dd1e47bb274507d4ff22cd1816",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-03-19T17:42:46Z",
    "title_canon_sha256": "648fc89bfa38d941e16185ea3bd6d094c500c913227d7e0133265f783e9a44c7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.19185",
    "kind": "arxiv",
    "version": 2
  }
}