HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework

arXiv:2607.23597v1 Announce Type: cross Abstract: Generative linguistic steganography conceals secret bits within the sampling randomness of large language models. Existing schemes are single-stream, conveying an entire secret through a single response to a single prompt. This convention incurs two limitations: it provides no protocol-level support for batched multi-stream inference, and naive co-batching does not conceal slot occupancy or payload completion. We propose HiTMS, which distributes a secret across multiple responses produced jointly over successive rounds of interaction. Each round embeds and extracts several streams within a single batched call, thereby amortizing the cost of model invocation and substantially improving throughput. To ensure recoverability, HiTMS wraps each response in a self-describing frame and employs a key-derived schedule that binds streams to slots and fills unused slots with decoys, guaranteeing exact recovery while concealing the number of active streams. The framework is agnostic to both the language model and the steganographic coder. Across eight dataset-model-coder settings, eight-stream HiTMS achieves up to 4.3 times higher embedding and extraction speeds than single-stream baselines, while reducing the steganalyzer AUROC from 0.681 to 0.601 on average. Additional experiments with 4 to 64 streams demonstrate sustained throughput gains as concurrency increases. GitHub repository for this work is https://github.com/ryehr/HiTMS_steganography.

Abstract:Generative linguistic steganography conceals secret bits within the sampling randomness of large language models. Existing schemes are single-stream, conveying an entire secret through a single response to a single prompt. This convention incurs two limitations: it provides no protocol-level support for batched multi-stream inference, and naive co-batching does not conceal slot occupancy or payload completion. We propose HiTMS, which distributes a secret across multiple responses produced jointly over successive rounds of interaction. Each round embeds and extracts several streams within a single batched call, thereby amortizing the cost of model invocation and substantially improving throughput. To ensure recoverability, HiTMS wraps each response in a self-describing frame and employs a key-derived schedule that binds streams to slots and fills unused slots with decoys, guaranteeing exact recovery while concealing the number of active streams. The framework is agnostic to both the language model and the steganographic coder. Across eight dataset-model-coder settings, eight-stream HiTMS achieves up to 4.3 times higher embedding and extraction speeds than single-stream baselines, while reducing the steganalyzer AUROC from 0.681 to 0.601 on average. Additional experiments with 4 to 64 streams demonstrate sustained throughput gains as concurrency increases. GitHub repository for this work is this https URL.

Cryptography and Security (cs.CR); Computation and Language (cs.CL)

arXiv:2607.23597 [cs.CR]

(or arXiv:2607.23597v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2607.23597 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework

Related coverage