{
  "id": 12244,
  "url": "https://arxiv.org/abs/2607.16620v1",
  "title": "Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning",
  "summary": "Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems. Prior work has shown that DP-SGD can widen accuracy disparities across demographic groups, but this framing treats fairness as a purely outcome-side concern. We argue that privacy cost, the information leakage borne by each group, is itself a form of harm, and adopt a compensatory-fairness framework in which a group that involuntarily bears greater privacy exposure is owed proportio",
  "authors": "Rakshit Naidu",
  "category": "research",
  "topics": "bias-fairness,privacy-surveillance",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-18T03:41:01.000Z",
  "fetched_at": "2026-07-21T05:10:12.656Z",
  "source_slug": "x-arxiv-cs-cr-ai-security",
  "source_name": "arXiv cs.CR (AI security)",
  "source_homepage": "https://arxiv.org/list/cs.CR/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/12244",
  "original_url": "https://arxiv.org/abs/2607.16620v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}