4 papers
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…
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…
Quantum Chemistry Simulation of Dibenzothiophene for Asphalt Aging Analysis
Om Tailor
This paper presents the execution and analysis of a comprehensive quantum chemistry pipeline for gathering actionable insight into asphalt aging mechanisms through the study of dib…
Audit the Whisper: Detecting Steganographic Collusion in Multi-Agent LLMs
Om Tailor
Multi-agent deployments of large language models (LLMs) are increasingly embedded in market, allocation, and governance workflows, yet covert coordination among agents can silently…