{
  "id": 5555,
  "url": "https://arxiv.org/abs/2604.19219v2",
  "title": "Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers",
  "summary": "Federated Learning (FL) enables collaborative model training among multiple parties without centralizing raw data. There are two main paradigms in FL: Horizontal FL (HFL), where all participants share the same feature space but hold different samples, and Vertical FL (VFL), where parties possess complementary features for the same set of samples. A prerequisite for VFL training is privacy-preserving entity alignment (PPEA), which establishes a common index of samples across parties (alignment) w",
  "authors": "Daniel M. Jimenez-Gutierrez, Dario Pighin, Enrique Zuazua, Georgios Kellaris, Joaquin Del Rio, Oleksii Sliusarenko et al.",
  "category": "research",
  "topics": "safety-alignment,privacy-surveillance,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-21T08:24:07.000Z",
  "fetched_at": "2026-07-14T16:31:48.877Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5555",
  "original_url": "https://arxiv.org/abs/2604.19219v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}