Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
Om Tailor, Yucheng Pan, Solaleh Mohammadi +2
In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as text transmitted to a decoder, who attempts to recover it. The…
cs.CR2026
Verifier-Bound Communication for LLM Agents: Certified Bounds on Covert Signaling
Om Tailor
Colluding language-model agents can hide coordination in messages that remain policy-compliant at the surface level. We present CLBC, a protocol where generation and admission are…