Synchronized Logit Steering: Real-world Steganography

• URL: http://arxiv.org/abs/2608.14697v1
• Date: Sun, 09 Aug 2026 22:49:45 GMT
• Title: Synchronized Logit Steering: Real-world Steganography
• Abstract summary: We introduce Synchronized Logit Steering (SLS)<n>SLS encodes payload values as token ranks within high-entropy regions of the proxy prompt distribution.<n>We extend the scheme with periodic recurrence and payload bursts to scale information density.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text. Existing token and logit-level methods typically require the sender and receiver to share an identical prompt context, which is rarely guaranteed in production pipelines that use retrieval-augmented generation or proprietary system instructions. We introduce Synchronized Logit Steering (SLS), a deterministic steganographic scheme that eliminates this dependency by deriving a proxy prompt from the generated output itself, allowing both parties to reconstruct the same logit distribution without access to the original prompt. SLS encodes payload values as token ranks within high-entropy regions of the proxy prompt distribution, and we extend the scheme with periodic recurrence and payload bursts to scale information density. Across ShareGPT, GSM8K, and SWE-bench Verified, we show that the KL divergence between the true and proxy prompt distributions falls below 0.5 nats once the synchronization window reaches 40 tokens, and SLS encoding does not meaningfully disrupt this convergence relative to greedy generation. We also find that the periodic-burst variant achieves 0.20 bits per token, or roughly 10x the capacity of single-payload encoding. Kolmogorov-Smirnov tests further confirm that SLS outputs are statistically difficult to distinguish from greedy generations, demonstrating that covert, prompt-agnostic communication through LLMs is both practical and stealthy.

Related papers

• AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling [60.04959047453115]
  AURORA-LM is a continuous-latent language model that separates the construction of a decodable text representation from the modeling of its distribution.<n>AURORA-LM achieves the strongest performance among evaluated continuous and diffusion-based language models on OpenWebText free generation and XSum summarization.
  arXiv  Detail & Related papers  (2026-08-03T17:59:50Z)
• Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing [65.59464371673623]
  Local Branch Routing (LBR) is a token-level test-time scaling framework.<n>It expands a small local lookahead tree, forwards all sampled branches through the language model, and uses a lightweight router to select the depth-1 subtree to commit.<n>LBR allows each token decision to use evidence beyond the root next-token distribution while avoiding full solution-level search.
  arXiv  Detail & Related papers  (2026-06-24T03:42:44Z)
• VCT: A Verifiable Transcript System for LLM Conversations [5.3181399750078535]
  Verifiable Conversation Transcript builds non-linear LLM semantic operations into account-level authenticated state transitions.<n>Security analysis demonstrates that, under standard cryptographic assumptions, VCT guarantees the integrity, consistency, verifiable shareability, and non-repudiation of account-level conversation records.
  arXiv  Detail & Related papers  (2026-06-22T08:17:39Z)
• Steganography Without Modification: Hidden Communication via LLM Seeds [4.729777380019769]
  We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions.<n>A sender encodes a secret message in the PRNG seed before generation; a receiver reconstructs the intervals and recovers the seed, and thus the hidden payload.<n>In the known-prompt setting, full 32-bit seed recovery from the complete 232 candidate space achieves up to 100% accuracy, depending on model and text domain.
  arXiv  Detail & Related papers  (2026-06-08T07:32:44Z)
• NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting [3.6732711233211663]
  NLLog is a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences.<n>It pools them with term-frequency-inverse-document-frequency weighting, classifies sessions with tree ensembles, and back-projects evidence.<n>It sustains low false-positive rates with commodity- hardware latency suitable for security operations center triage.
  arXiv  Detail & Related papers  (2026-06-03T14:45:29Z)
• ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography [28.687186883782033]
  Generative linguistic steganography enables covert communication by embedding secret messages into the natural language generation process.<n>The same surface text may be re-tokenized into a different token sequence at the receiver, breaking the shared decoding state.<n>We propose ReTokSync, a framework that monitors the receiver-view tokenization during generation and triggers a corrective reset only when ambiguity actually occurs.
  arXiv  Detail & Related papers  (2026-04-28T10:42:43Z)
• WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference [56.297697169678095]
  WISV (Wireless-Informed Semantic Verification) is a novel distributed speculative decoding framework.<n>We show that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency.<n>We validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server.
  arXiv  Detail & Related papers  (2026-04-20T01:29:56Z)
• CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language [21.764828393078886]
  Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation.<n>We address these limitations by shifting the diffusion process into a continuous sentence-level semantic space.
  arXiv  Detail & Related papers  (2026-03-02T12:50:55Z)
• Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions [60.43398881149664]
  We introduce LOS-Net, a lightweight attention-based architecture trained on an efficient encoding of the LLM Output Signature.<n>It achieves superior performance across diverse benchmarks and LLMs, while maintaining extremely low detection latency.
  arXiv  Detail & Related papers  (2025-03-18T09:04:37Z)
• Nearest Neighbor Speculative Decoding for LLM Generation and Attribution [87.3259169631789]
  Nearest Speculative Decoding (NEST) is capable of incorporating real-world text spans of arbitrary length into the LM generations and providing attribution to their sources.<n>NEST significantly enhances the generation quality and attribution rate of the base LM across a variety of knowledge-intensive tasks.<n>In addition, NEST substantially improves the generation speed, achieving a 1.8x speedup in inference time when applied to Llama-2-Chat 70B.
  arXiv  Detail & Related papers  (2024-05-29T17:55:03Z)
• Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models [94.30953696090758]
  We build compositional end-to-end spoken language understanding systems. By relying on intermediate decoders trained for ASR, our end-to-end systems transform the input modality from speech to token-level representations. Our models outperform both cascaded and direct end-to-end models on a labeling task of named entity recognition.
  arXiv  Detail & Related papers  (2022-10-27T19:33:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.