Review: LLMGuard�Defense-in-Depth for Production Prompts
Abstract
We catalog prompt hardening, output filters, and model routing, with cost/latency tradeoffs for production LLM stacks.
Cite this article
Zhou, O., Zhou, Q., & Havel, L. (2023). Review: LLMGuard�Defense-in-Depth for Production Prompts. Research Explorations in Global Knowledge & Technology (REGKT), 2 (9). Retrieved from https://regkt.com/article.php?id=467&slug=review-llmguard-defense-in-depth-production-prompts