{
  "id": 3617,
  "url": "https://arxiv.org/abs/2605.28030v1",
  "title": "SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection",
  "summary": "Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversarial data removes safeguards and induces unsafe behaviors. We propose SPARD, a defense framework that integrates Safety-Projected Alternating optimization with Relevance-Diversity aware data selection. SPARD employs SPAG, which optimizes alternatively between utility updates and explicit safety projections with a set of safe data to enforce safety ",
  "authors": "Shuhao Chen, Weisen Jiang, Yeqi Gong, Shengda Luo, Chengxiang Zhuo, Zang Li et al.",
  "category": "research",
  "topics": "safety-alignment,military-security",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-27T06:36:22.000Z",
  "fetched_at": "2026-07-14T16:30:23.246Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3617",
  "original_url": "https://arxiv.org/abs/2605.28030v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}