提出锚点滑动窗口，让文本隐写更隐蔽且抗修改。
Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography
- 用锚点+桥接上下文保持模型生成连贯性
- 在多种场景下提升文本质量与抗干扰能力
- 适合对隐蔽性和鲁棒性要求高的应用
基于语言模型的自然语言隐写通常假设文本传输过程中不被修改，因此对微小变动极为敏感。现有方法通过限制上下文窗口缓解此问题，但严重损害文本质量。本文提出锚点滑动窗口（ASW）框架，在上下文窗口中固定最新词元、提示词和桥接上下文，促使模型补偿被排除的词元。我们将桥接上下文优化建模为提示蒸馏的变体，并进一步引入自蒸馏策略。实验表明，ASW在不同设置下显著且一致地优于基线方法，在文本质量、隐蔽性和鲁棒性方面均有提升。代码已开源：github.com/ryehr/ASW_steganography。
原文摘要 · Abstract (English)
Linguistic steganography based on language models typically assumes that steganographic texts are transmitted without alteration, making them fragile to even minor modifications. While previous work mitigates this fragility by limiting the context window, it significantly compromises text quality. In this paper, we propose the anchored sliding window (ASW) framework to improve imperceptibility and robustness. In addition to the latest tokens, the prompt and a bridge context are anchored within the context window, encouraging the model to compensate for the excluded tokens. We formulate the optimization of the bridge context as a variant of prompt distillation, which we further extend using self-distillation strategies. Experiments show that our ASW significantly and consistently outperforms the baseline method in text quality, imperceptibility, and robustness across diverse settings. The code is available at github.com/ryehr/ASW_steganography.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。