Visual Context Injection

via “visual prompt injection vulnerability testing”

Meta's safety classifier for LLM content moderation.

Unique: First industry benchmark for visual prompt injection attacks on multimodal LLMs, recognizing that vision-language models introduce new attack surface beyond text. Includes steganographic and adversarial visual patterns, not just text-in-image injection.

vs others: Addresses a gap in existing safety benchmarks which focus exclusively on textual attacks; visual injection is a distinct threat vector for multimodal models that requires separate evaluation.