{
  "id": 11863,
  "url": "https://arxiv.org/abs/2607.15970v1",
  "title": "Code-Poisoning Property Inference Attacks",
  "summary": "The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning (ML) models using available code quickly. The training data for ML models, often regarded as private property (e.g., clinical records, transaction information), is at significant risk of information leakage. Property Inference Attacks (PIAs), as a significant type of privacy attack, aim to expose global property information of the training set. In this paper, we pre",
  "authors": "Xukun Luan, Yuhui Gong, Gang Zhang, Zixuan Huang, Yuanguo Bi, Xuesong Li, Jinyan Liu",
  "category": "research",
  "topics": "privacy-surveillance,healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T14:04:59.000Z",
  "fetched_at": "2026-07-20T05:10:09.534Z",
  "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/11863",
  "original_url": "https://arxiv.org/abs/2607.15970v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}