TL;DR
This paper introduces the anchored sliding window framework for linguistic steganography, enhancing text imperceptibility and robustness by anchoring prompt and bridge context, with optimization via prompt distillation.
Contribution
The paper proposes the ASW framework that improves linguistic steganography robustness and imperceptibility through anchored context and novel optimization strategies.
Findings
ASW outperforms baseline in text quality, imperceptibility, and robustness.
Anchoring prompt and bridge context enhances model compensation for excluded tokens.
Self-distillation strategies further improve steganography performance.
Abstract
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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
