"PromptShield team on AMD Developer Hackathon Hackathon"

Team Idea

A 4-layer agentic pipeline that detects and blocks prompt injection attacks in real-time — the missing security layer for every AI deployment.

Team Members

Unknown Hacker

sarthak700281372

Submission

IntelliGuard - Injection Defense for Enterprise AI

A 4-layer AI security pipeline detecting prompt injection attacks in real-time. Fine-tuned on 88k adversarial samples on AMD MI300X. Protects RAG systems from direct, encoded, multilingual, and poetic attacks.