SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use

Computer Science > Cryptography and Security [Submitted on 10 Jan 2026 (v1), last revised 14 May 2026 (this version, v2)] SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use Pratyush Desai, Luoxi Tang, Yuqiao Meng, Zhaohan Xi 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. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2601.06366 [cs.CR]   (or arXiv:2601.06366v2 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2601.06366 Focus to learn more Submission history From: Luoxi Tang [view email] [v1] Sat, 10 Jan 2026 00:33:38 UTC (786 KB) [v2] Thu, 14 May 2026 19:11:52 UTC (790 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-01 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)