Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding
Jiaming Shen, Heng Ji, Jiawei Han
Abstract
Linguistic steganography studies how to hide secret messages in natural language cover texts. Traditional methods aim to transform a secret message into an innocent text via lexical substitution or syntactical modification. Recently, advances in neural language models (LMs) enable us to directly generate cover text conditioned on the secret message. In this study, we present a new linguistic steganography method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model. We formally analyze the statistical imperceptibility of this method and empirically show it outperforms the previous state-of-the-art methods on four datasets by 15.3% and 38.9% in terms of bits/word and KL metrics, respectively. Finally, human evaluations show that 51% of generated cover texts can indeed fool eavesdroppers. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
7 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers7
- Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language ModelsRuiyi Yan, Yugo MurawakiEMNLP 2025
- Efficient Provably Secure Linguistic Steganography via Range CodingRuiyi Yan, Yugo MurawakiACL 2026
- A Content-Preserving Secure Linguistic SteganographyLingyun Xiang, Chengfu Ou, Xu He, Zhongliang Yang et al.AAAI 2026
- Provably Robust and Secure Steganography in Asymmetric Resource ScenarioMinhao Bai, Jinshuai Yang, Kaiyi Pang, Xin Xu et al.S&P 2025
- A Framework for Designing Provably Secure SteganographyGuorui Liao, Jinshuai Yang, Weizhi Shao, Yongfeng HuangUSENIX Security 2025
Related papers
- Provably Secure Generative Linguistic SteganographySi-yu Zhang, Zhongliang Yang, Jinshuai Yang, Yongfeng HuangACL Findings 2021 · 101 citations
- STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language ModelYuang Qi, Na Zhao, Qiyi Yao, Benlong Wu et al.NeurIPS 2025 · 4 citations
- Promising Multi-Granularity Linguistic Steganography by Jointing Syntactic and Lexical ManipulationsChengfu Ou, Lingyun Xiang, Yangfan LiuAAAI 2025
- Steganography Beyond Pixels: Reimagining Image Steganography as Cross-Modal Linguistic CommunicationLijing Ren, Denghui ZhangACL 2026
- Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text SteganographyJiuan Zhou, Yu Cheng, Yuan Xie, Zhaoxia YinACL Findings 2026
