Paper

SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)

Unreadunread

AI summary

arXiv:2606. 08372v1 Announce Type: new Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute values from a synthetic release and a handful of known quasi-identifiers) has been studied only in scattered, hard-to-compare settings.

Reading status

Priority

About this paper

Authors: Steven Golob, Sikha Pentyala, Martine De Cock
Released: 2026-06-09 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC) overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: strong, text, fill, distributional, eval, compare, test. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2606.08372

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC). Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.