{
  "id": 3954,
  "url": "https://arxiv.org/abs/2605.22880v1",
  "title": "How Far Will They Go? Red-Teaming Online Influence with Large Language Models",
  "summary": "As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal, we focus on locally deployed open-source LLMs, as opposed to frontier API-only models, given their superior alignment with the operational constraints of privacy-conscious malicious actors deployed in social media environments. We introduce an empirical red-teaming framework for",
  "authors": "Daniel C. Ruiz, Anna Serbina, Ashwin Rao, Emilio Ferrara, Luca Luceri",
  "category": "research",
  "topics": "safety-alignment,privacy-surveillance,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-20T19:25:26.000Z",
  "fetched_at": "2026-07-14T16:30:36.744Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3954",
  "original_url": "https://arxiv.org/abs/2605.22880v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}