A Guardrail Framework for Sensitive Financial Information Protection: A Taxonomy-Driven Approach

We propose GARD, a domain-specific “guardrail” framework designed to detect and block sensitive financial information (SFI) in both inputs and outputs of large language models (LLMs). Unlike general-purpose content filters, GARD is built upon a comprehensive, taxonomy of SFI distilled from financial-services regulations (GLBA, PCI-DSS, FFIEC), information-security standards (ISO 27001, NIST SP 800-53/122/171), and enterprise policies. Leveraging this taxonomy, we synthesized a 17,495-sample dataset of risky and non-risky financial texts using multiple LLMs (Gemini 1.5, Mixtral-8x7B, GPT-4o, Llama 3.1) and real-world prompts. Each sample was embedded via OpenAI’s text-embedding-ada-002 and used to train a generative-adversarial network (GARD), where the discriminator learns to distinguish SFI-laden vectors. On a held-out test set of 3,552 samples, GARD achieved 0.98 recall and 0.92 F1, markedly outperforming the OpenAI Moderation API (recall 0.30) and Azure Content Safety (recall 0.37) while sustaining over 50 prompts/sec throughput. Our contributions are threefold: (1) a grounded, granular taxonomy of SFI for GenAI guardrails; (2) an extensible, synthetic SFI dataset; and (3) GARD, a high-performance risk detector that can augment or replace existing commercial solutions. This taxonomy-driven approach advances AI safety, regulatory compliance, and responsible GenAI adoption in financial services.