{
  "annotation_id": "3384d47a-9e90-41e0-aef6-aa81a2674162",
  "date_created": "2026-02-17T05:53:07.571000Z",
  "date_modified": "2026-02-17T05:53:07.571000Z",
  "file_hash": "0521ed13b95230845d57b9e3b4692eadbb3307b7f027d627a464453cde16634e",
  "private": false,
  "record": {
    "abstract": "Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate policy-violating content. This paper proposes SafeGPT, a two-sided guardrail system preventing sensitive data leakage and unethical outputs. SafeGPT integrates input-side detection/redaction, output-side moderation/reframing, and human-in-the-loop feedback. Experiments demonstrate SafeGPT effectively reduces data leakage risk and biased outputs while maintaining satisfaction.",
    "arxiv_id": "2601.06366",
    "authors": [
      "Pratyush Desai",
      "Luoxi Tang",
      "Yuqiao Meng",
      "Zhaohan Xi"
    ],
    "categories": [
      "cs.CR",
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use",
    "url": "https://arxiv.org/abs/2601.06366",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "bee6baa2-e1be-4277-b06b-a54822740da5",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}