Practical Cybersecurity Architecture and AI Security

security made simple

secdoc.tech

Featured

Inspect Both Sides of the LLM Conversation
ai-security · Featured

Inspect Both Sides of the LLM Conversation

A practical policy and configuration guide for detecting prompt injection and jailbreak attempts before inference, then blocking unsafe content and sensitive-data disclosure before model output reaches a user, tool, or application.

Latest

Inspect Both Sides of the LLM Conversation
ai-security · Featured

Inspect Both Sides of the LLM Conversation

A practical policy and configuration guide for detecting prompt injection and jailbreak attempts before inference, then blocking unsafe content and sensitive-data disclosure before model output reaches a user, tool, or application.