embedding-drift

Tag

Cards List
#embedding-drift

Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs

arXiv cs.AI · 2026-06-08 Cached

This paper introduces Zero-Shot Embedding Drift Detection (ZEDD), a lightweight framework that detects prompt injection attacks in LLMs by measuring semantic shifts in embedding space, achieving over 93% accuracy with less than 3% false positive rate across multiple architectures.

0 favorites 0 likes
← Back to home

Submit Feedback