TI-StegoAlign: Channel-Guided Post-Training for Generative Text Steganography under Tokenization Inconsistency

• URL: http://arxiv.org/abs/2608.00382v1
• Date: Sat, 01 Aug 2026 01:45:50 GMT
• Title: TI-StegoAlign: Channel-Guided Post-Training for Generative Text Steganography under Tokenization Inconsistency
• Abstract summary: LLM agents exchange secret information through task-relevant messages.<n>Most methods evaluate recovery on sender-side tokens, whereas the receiver observes only surface text.<n>Detokenization and receiver-side retokenization can alter token boundaries, desynchronize coding states, and cause such evaluation to overestimate receiver-side recovery.<n>We propose TI-StegoAlign, a channel-guided post-training framework.
• Score: 20.336143930874993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative text steganography enables LLM agents to exchange secret information through task-relevant messages. Yet most methods evaluate recovery on sender-side tokens, whereas the receiver observes only surface text. Detokenization and receiver-side retokenization can alter token boundaries, desynchronize coding states, and cause such evaluation to overestimate receiver-side recovery. Existing remedies rely on inference-time filtering or verification, correcting individual outputs without adapting the generation policy to the receiver-side channel. To address these limitations, we propose TI-StegoAlign, a channel-guided post-training framework. The Bit-Consistent Supervised Objective (BCSO) enlarges local coding margins at realized sender-side embedding positions. Channel-Conditioned Preference Optimization (CCPO) then aligns complete stegotexts using receiver-realistic recovery, text quality, and anti-steganalysis feedback. TI-StegoAlign updates only LoRA parameters and requires no tokenization-specific correction during communication. Experimental results show 100% receiver bit accuracy. Compared with the strongest baselines, TI-StegoAlign achieves a 21.6% reduction in normalized perplexity deviation and a 6.3% relative improvement in anti-steganalysis performance.

Related papers

• PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning [4.349000444958713]
  We introduce PACE, which treats collaborative knowledge as a compact correction to a complete Local predictor.<n>Each client uploads a rank-r update carrier and a diagonal sketch of propagated message moments.<n>The server uses them to construct a propagation-aware, receiver-anchored correction, while the receiver retains its full Local model.
  arXiv  Detail & Related papers  (2026-09-04T07:44:12Z)
• Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication [10.362447715626388]
  Gated Counterfactual Refinement for Communication (GCR-C) is a rollout-style correction layer over Local-MDL.<n>GCR-C consistently improves reconstruction quality at active low- and medium-rate operating points without increasing the realized packet rate.<n>Results also reveal a clear quality--computation tradeoff due to the additional encoder-side counterfactual evaluation.
  arXiv  Detail & Related papers  (2026-08-17T07:16:37Z)
• Conformal Certification of Reasoning Trace Prefixes [30.432255322700126]
  We introduce CROP (Conformal Reasoning Output Prefixes), a verifier-agnostic calibration procedure for clean- annotated certification.<n>We demonstrate that CROP over- and under-withholding, improving downstream repair accuracy by preserving valid intermediate reasoning.
  arXiv  Detail & Related papers  (2026-05-28T15:31:42Z)
• Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights [58.27172968382275]
  Multi-agent LLM systems usually collaborate by exchanging natural-language messages.<n>We study an alternative communication interface: instead of appending a sender's message to the receiver's context, compile the sender's hidden states into a transient, receiver-specific weight perturbation.
  arXiv  Detail & Related papers  (2026-05-13T17:58:32Z)
• PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution [51.96078493242164]
  PRISM is a single-step diffusion-based Text-SR framework.<n> PRISM achieves state-of-the-art performance with millisecond-level inference.
  arXiv  Detail & Related papers  (2026-05-13T05:31:06Z)
• Reward-Guided Semantic Evolution for Test-time Adaptive Object Detection [82.2968697030677]
  Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts.<n>We propose Reward-Guided Semantic Evolution (RGSE), a training-free framework that directly refines the text embeddings at test time.
  arXiv  Detail & Related papers  (2026-05-06T06:17:41Z)
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs [61.06744611795341]
  Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging.<n>We propose texttttextbfLATA (Laplacian-Assisted Transductive Adaptation), a textittraining- and label-free refinement.<n>texttttextbfLATA sharpens zero-shot predictions without compromising exchangeability.
  arXiv  Detail & Related papers  (2026-02-19T16:45:38Z)
• Chain of Correction for Full-text Speech Recognition with Large Language Models [21.37485126269991]
  Chain of Correction (CoC) is a multi-turn chat format to correct errors segment by segment, guided by pre-recognized text and full-text context for better semantic understanding.<n> Experiments show that CoC significantly outperforms baseline and benchmark systems in correcting full-text ASR outputs.
  arXiv  Detail & Related papers  (2025-04-02T09:06:23Z)
• TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition [78.67283660198403]
  Text irregularities pose significant challenges to scene text recognizers. TPS++ is an attention-enhanced TPS transformation that incorporates the attention mechanism to text rectification. It consistently improves the recognition and achieves state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2023-05-09T10:16:43Z)
• Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation [80.12316877964558]
  High-quality data labeling from specific domains is costly and human time-consuming. We propose a self-supervised domain adaptation method, based upon an iterative pseudo-forced alignment algorithm.
  arXiv  Detail & Related papers  (2022-10-27T07:23:08Z)
• On Addressing Practical Challenges for RNN-Transduce [72.72132048437751]
  We adapt a well-trained RNN-T model to a new domain without collecting the audio data. We obtain word-level confidence scores by utilizing several types of features calculated during decoding. The proposed time stamping method can get less than 50ms word timing difference on average.
  arXiv  Detail & Related papers  (2021-04-27T23:31:43Z)

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.