SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use
For enterprises deploying LLMs, SafeGPT addresses the critical problem of data leakage and unethical content generation, but the approach is incremental.
SafeGPT introduces a two-sided guardrail system to prevent data leakage and unethical outputs in enterprise LLM use, effectively reducing leakage risk and biased outputs while maintaining user satisfaction.
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.