2026
Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
ICML 2026poster
Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We formalize payload recoverability via classifier accuracy and show previous schemes achieve 100\% recoverability. In respo…