{"ID":2858521,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.06565","arxiv_id":"2510.06565","title":"Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography","abstract":"With the rapid progress of LLMs, high quality generative text has become widely available as a cover for text steganography. However, prevailing methods rely on hand-crafted or pre-specified strategies and struggle to balance efficiency, imperceptibility, and security, particularly at high embedding rates. Accordingly, we propose Auto-Stega, an agent-driven self-evolving framework that is the first to realize self-evolving steganographic strategies by automatically discovering, composing, and adapting strategies at inference time; the framework operates as a closed loop of generating, evaluating, summarizing, and updating that continually curates a structured strategy library and adapts across corpora, styles, and task constraints. A decoding LLM recovers the information under the shared strategy. To handle high embedding rates, we introduce PC-DNTE, a plug-and-play algorithm that maintains alignment with the base model's conditional distribution at high embedding rates, preserving imperceptibility while enhancing security. Experimental results demonstrate that at higher embedding rates Auto-Stega achieves superior performance with gains of 42.2\\% in perplexity and 1.6\\% in anti-steganalysis performance over SOTA methods.","short_abstract":"With the rapid progress of LLMs, high quality generative text has become widely available as a cover for text steganography. However, prevailing methods rely on hand-crafted or pre-specified strategies and struggle to balance efficiency, imperceptibility, and security, particularly at high embedding rates. Accordingly,...","url_abs":"https://arxiv.org/abs/2510.06565","url_pdf":"https://arxiv.org/pdf/2510.06565v1","authors":"[\"Jiuan Zhou\",\"Yu Cheng\",\"Yuan Xie\",\"Zhaoxia Yin\"]","published":"2025-10-08T01:32:59Z","proceeding":"cs.CR","tasks":"[\"cs.CR\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}