steganography-detection

Tag

Cards List
#steganography-detection

MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents

arXiv cs.CL · 2026-06-10 Cached

This paper identifies a polarity-flipping encoding subspace in the residual stream of LLM agents that enables real-time detection of covert data exfiltration, achieving AUC=0.918 in injection scenarios and substantially outperforming output-only detectors.

0 favorites 0 likes
← Back to home

Submit Feedback