Research
STEALTH: Steganographic Text Encoding Agnostic to Low-Level Tensor Hardware
Researchers show that bit-exact linguistic steganography fails when receiver hardware, precision, quantization, or scoring mode differs from the sender's setup. They introduce STEALTH, which uses keyed pseudorandom noise and a rateless spinal code decoded by beam search to absorb token-level probability mismatches. The scheme decodes messages across model families, tokenizers, precision levels, and GPU architectures while preserving indistinguishability from honest model output.
linguistic steganographylanguage model samplinghardware robustness