Conformal Privacy Auditing: Calibrated Re-identification Attacks with Statistical Guarantees
Conformal Privacy Auditing certifies per-document re-identification risk against LLM attackers with statistical coverage guarantees.
Conformal Privacy Auditing is a distribution-free method that certifies re-identification risk for each released text document against adversaries that combine large language models with auxiliary knowledge. For a user-chosen confidence level, it returns a conformal ambiguity set guaranteed, under exchangeability, to contain the true identity, and it treats set size as a leakage proxy. It supports both logit-access and sampling-only attackers, so open-weight models and proprietary APIs can be audited in one framework. Across release benchmarks, certified identifiability changed sharply with auxiliary knowledge, LLM augmentation, and the release mechanism.
- CPA issues a per-document conformal set guaranteed to contain the true identity at a chosen confidence.
- Set size is used as an interpretable leakage proxy.
- The method covers logit-access and sampling-only attackers, including proprietary APIs.
- Audits show identifiability shifts with auxiliary knowledge, LLM use, and release mechanisms.
From the original article
1 min read at arxiv.orgEmpirical identity leakage from released text is increasingly driven by attackers that combine large language models (LLMs) with auxiliary knowledge to link documents to individuals.
By Shuo Huang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.