Pith. sign in

REVIEW 4 cited by

TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2211.06550 v1 pith:ZRBHXLYO submitted 2022-11-12 cs.CR cs.AIcs.LG

Florimond Houssiau , James Jordon , Samuel N. Cohen , Owen Daniel , Andrew Elliott , James Geddes , Callum Mole , Camila Rangel-Smith
show 1 more author
Lukasz Szpruch
This is my paper · ORCID
classification cs.CRcs.AIcs.LG
keywords dataprivacysyntheticattackstapashoweverrealrecords
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Personal data collected at scale promises to improve decision-making and accelerate innovation. However, sharing and using such data raises serious privacy concerns. A promising solution is to produce synthetic data, artificial records to share instead of real data. Since synthetic records are not linked to real persons, this intuitively prevents classical re-identification attacks. However, this is insufficient to protect privacy. We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios. These attacks include generalizations of prior works and novel attacks. We also introduce a general framework for reasoning about privacy threats to synthetic data and showcase TAPAS on several examples.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation

    cs.LG 2025-07 conditional novelty 6.0 of 10

    LLM-based tabular generators reproduce seed rows often enough that membership-inference attacks succeed more against them than against GAN, VAE, or diffusion baselines.

  2. Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGN

    cs.LG 2025-08 unverdicted novelty 5.0 of 10

    TabularARGN is a discretization-based auto-regressive network claimed to generate high-fidelity, privacy-robust synthetic tabular data, competitive with diffusion and GAN baselines.

  3. Synthetic Tabular Data: Methods, Attacks and Defenses

    cs.LG 2025-06 conditional novelty 1.0 of 10

    A review of tabular synthetic data generation, privacy attacks, and defenses, whose central message is that synthetic data alone does not guarantee privacy.

  4. Synthetic Data Privacy Metrics

    cs.LG 2025-01 unverdicted

    This preprint reviews existing privacy metrics for synthetic data and privacy-enhancing techniques, and argues that the field lacks standardization.

Pith tools