Physical Prompt Injection Attacks

Defend against and red-team physical prompt injection attacks on Large Vision-Language Models (LVLMs). Build input sanitization pipelines, attention-aware OCR filters, and robustness test harnesses that detect typographic instructions embedded in images before they reach the model. Trigger phrases: "harden my vision model against prompt injection", "detect text injection in images", "red team my LVLM pipeline", "build an image input sanitizer for VLMs", "test physical prompt attacks", "PPIA defense pipeline"

ndpvt-web Updated 14 repo stars

File contents

ndpvt-web/arxiv-claude-skills commit 956d1ca88a

Frequently asked questions

npx get-skill add ndpvt-web/physical-prompt-injection-attacks