mlsanityData to 7 Oct 2026

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

arXiv 2601.06366 ↗First posted 10 Jan 2026cs.CR cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 16 of its 38 references that are in the map. First posted on arXiv 10 Jan 2026.

Builds on

16 of 38 references.

References · 16

  1. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  2. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  5. 2021Ethical and social risks of harm from Language Modelscited by 957
  6. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  7. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 380
  8. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 347
  9. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  10. 2017Deceiving Google's Perspective API Built for Detecting Toxic Commentscited by 99
  11. 2023Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attackscited by 32
  12. 2019Towards Robust Toxic Content Classificationcited by 22
4 more
  1. 2024Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnosticscited by 11
  2. 2024PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuningcited by 2
  3. 2025POLAR: Automating Cyber Threat Prioritization through LLM-Powered Assessmentcited by 2
  4. 2026Schema-Grounded LLM Extraction for FHIR Patient Digital Twinscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Generating Leakage-Free Benchmarks for Robust RAG Evaluationcited by 0
  2. 2026Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Auditcited by 0