{
  "id": 3055,
  "url": "https://arxiv.org/abs/2606.26036v1",
  "title": "Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning",
  "summary": "Training-time data poisoning during fine-tuning poses a significant threat to large language models (LLMs) deployed for abstractive text summarization, where small task-specific datasets exert disproportionate influence on model behavior. In this setting, adversaries manipulate fine-tuning data to induce persistent summarization failures, such as biased or harmful summaries, while preserving standard evaluation metrics. We present a unified post-hoc defense framework for detecting and remediatin",
  "authors": "Poojitha Thota, Shirin Nilizadeh",
  "category": "research",
  "topics": "bias-fairness,military-security",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-24T17:12:42.000Z",
  "fetched_at": "2026-07-14T16:11:46.979Z",
  "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/3055",
  "original_url": "https://arxiv.org/abs/2606.26036v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}