<ul data-eligibleForWebStory="false"><li>Proxy-based policy engines provide a robust way to protect Language Model Models (LLMs) from threats by inserting a proxy between users and the model.</li><li>Defenses live in the proxy, removing the need to fine-tune every new LLM model version for security risks, and enabling centralized management of multiple models.</li><li>LlamaGuard and PromptGuard are LLM-based classifiers for filtering input/output to detect attacks, while open-source proxy tools like Usage Panda can monitor and control LLM traffic.</li><li>Relying on a proxy-based layer with a policy engine enhances LLM security, ensuring they behave reliably and safely without changing base models.</li></ul>

Building Safer LLMs: How Proxy-Based Policy Engines Stop Prompt Injection

Discover more