A False Sense of Privacy: Azure PII tool fails to protect 74% of MedQA data
niloofar_mire · x · 2026-09-09
Citing the paper 'A False Sense of Privacy' (arXiv:2504.21035), the author shows that PII removal and synthetic data generation don't guarantee privacy: innocuous auxiliary info like routine social activities can re-identify sensitive attributes (age, substance use history) from sanitized text. Azure's commercial PII tool fails to protect 74% of information in MedQA; differential privacy helps but hurts downstream utility. Synthetic data carries re-identification risks too.
More from Safety
- Mollick: WeWorm demo and Hugging Face incident show no company is worried enough about cybersecurity — emollick · 2026-09-09
- China targets 9,800 EFLOPS of AI computing capacity by 2030, a fourfold boost — pstAsiatech · 2026-09-09
- Anthropic quits major tech group ITI over chip export-control stance — pstAsiatech · 2026-09-09
- Meta Muse uses a separate Sentinel to gate agent outbound actions—what should you test first? — Crescitaly · 2026-09-09
- Provably private inference services promise prompts unreadable to providers — corbtt · 2026-09-09
- Google says EU DMA rules caused the biggest Search quality drop in its 29-year history — rickasaurus · 2026-09-09