深度学习让语言隐写检测更准，这篇综述系统梳理了当前进展。
State-of-the-art Advances of Deep-learning Linguistic Steganalysis Research
- 提出语言隐写分析通用公式，区分其与文本分类的本质差异
- 按向量映射与特征提取分两层归纳现有方法，对比优劣
- 指出领域瓶颈并给出未来研究方向，适合关注安全与模型的读者
随着生成式语言隐写技术的发展，传统隐写分析难以有效量化隐写带来的修改，导致检测困难。因此研究范式转向基于深度学习的语言隐写分析。本文全面回顾现有成果，评估主流发展路径。首先，形式化定义语言隐写分析通用公式，并比较该领域与文本分类的差异；其次，根据向量空间映射和特征提取模型，将已有工作分为两个层次，比较研究动机、模型优势等细节；通过实验对比分析性能表现；最后，讨论该领域面临挑战，提出未来发展方向及亟需解决的关键问题。
原文摘要 · Abstract (English)
With the evolution of generative linguistic steganography techniques, conventional steganalysis falls short in robustly quantifying the alterations induced by steganography, thereby complicating detection. Consequently, the research paradigm has pivoted towards deep-learning-based linguistic steganalysis. This study offers a comprehensive review of existing contributions and evaluates prevailing developmental trajectories. Specifically, we first provided a formalized exposition of the general formulas for linguistic steganalysis, while comparing the differences between this field and the domain of text classification. Subsequently, we classified the existing work into two levels based on vector space mapping and feature extraction models, thereby comparing the research motivations, model advantages, and other details. A comparative analysis of the experiments is conducted to assess the performances. Finally, the challenges faced by this field are discussed, and several directions for future development and key issues that urgently need to be addressed are proposed.
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。