This paper introduces the Generative Application Firewall (GAF), a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-masking -- remain fragmented; GAF unifies them into a single enforcement point, much like a WAF coordinates defenses for web traffic, while also covering autonomous agents and their tool interactions.

翻译：本文介绍了生成式应用防火墙（GAF），一种用于保护大语言模型（LLM）应用的新型架构层。现有的防御措施——提示过滤器、防护栏和数据掩码——仍然处于碎片化状态；GAF将它们统一到一个单一的强制执行点，类似于网络应用防火墙（WAF）协调针对网络流量的防御，同时它还覆盖了自主智能体及其工具交互。