{
  "id": 10535,
  "url": "https://arxiv.org/abs/2607.13039",
  "title": "Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants",
  "summary": "arXiv:2607.13039v1 Announce Type: new Abstract: Safety evaluations for dual-use biology assistants often measure base-model capability, refusal behavior, or jailbreak success. These metrics miss a deployment question: for a fixed base model, how does the access condition users actually see change benign utility and harmful actionable assistance? I introduce safeguard-conditioned uplift, a protocol for comparing deployed access conditions through a human-judged utility-risk frontier. I evaluate C",
  "authors": "Dipesh Tharu Mahato",
  "category": "research",
  "topics": "safety-alignment,biotech",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-16T04:00:00.000Z",
  "fetched_at": "2026-07-16T05:10:56.605Z",
  "source_slug": "arxiv-cscy",
  "source_name": "arXiv cs.CY",
  "source_homepage": "https://arxiv.org/list/cs.CY/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/10535",
  "original_url": "https://arxiv.org/abs/2607.13039",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}