English
Related papers

Related papers: Kolmogorov Complexity Bounds for LLM Steganography…

200 papers

We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely tend to achieve lower perplexity. Concretely, we find that…

Computation and Language · Computer Science 2026-04-21 Yanhong Li , Ming Li , Karen Livescu , Jiawei Zhou

The coding theorem for Kolmogorov complexity states that any string sampled from a computable distribution has a description length close to its information content. A coding theorem for resource-bounded Kolmogorov complexity is the key to…

Computational Complexity · Computer Science 2024-09-20 Shuichi Hirahara , Zhenjian Lu , Mikito Nanashima

Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can also covertly convey messages: a misaligned model may embed covert information in its CoT…

Computation and Language · Computer Science 2026-05-27 Zhejian Zhou , Jonathan May

In this paper, we make the first attempt towards defining cost function of steganography with large language models (LLMs), which is totally different from previous works that rely heavily on expert knowledge or require large-scale datasets…

Cryptography and Security · Computer Science 2025-12-25 Hanzhou Wu , Yige Wang

Steganography is the art and science of hiding data within innocent-looking objects (cover objects). Multimedia objects such as images and videos are an attractive type of cover objects due to their high embedding rates. There exist many…

Cryptography and Security · Computer Science 2025-01-27 Hassan Y. El-Arsh , Amr Abdelaziz , Ahmed Elliethy , Hussein A. Aly

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…

Computation and Language · Computer Science 2024-02-20 Kun Luo , Zheng Liu , Shitao Xiao , Kang Liu

To detect stego (steganographic text) in complex scenarios, linguistic steganalysis (LS) with various motivations has been proposed and achieved excellent performance. However, with the development of generative steganography, some stegos…

Computation and Language · Computer Science 2024-06-24 Yifan Tang , Yihao Wang , Ru Zhang , Jianyi Liu

Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local…

Computation and Language · Computer Science 2025-07-16 Yogachandran Rahulamathavan , Misbah Farooq , Varuna De Silva

Recent advances in large language models (LLMs) have blurred the boundary of high-quality text generation between humans and machines, which is favorable for generative text steganography. While, current advanced steganographic mapping is…

Computation and Language · Computer Science 2024-11-06 Jiaxuan Wu , Zhengxian Wu , Yiming Xue , Juan Wen , Wanli Peng

Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…

Computation and Language · Computer Science 2026-01-27 Kartik Sharma , Yiqiao Jin , Rakshit Trivedi , Srijan Kumar

Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal. Language is a particularly pragmatic cover…

Computation and Language · Computer Science 2019-09-05 Zachary M. Ziegler , Yuntian Deng , Alexander M. Rush

Rapid advancements of large language model (LLM) technologies led to the introduction of powerful open-source instruction-tuned LLMs that have the same text generation quality as the state-of-the-art counterparts such as GPT-4. While the…

Computation and Language · Computer Science 2024-12-31 Mikhail Tikhomirov , Daniil Chernyshev

To study how to design steganographic algorithm more efficiently, a new coding problem -- steganographic codes (abbreviated stego-codes) -- is presented in this paper. The stego-codes are defined over the field with $q(q\ge2)$ elements.…

Cryptography and Security · Computer Science 2009-09-29 Weiming Zhang , Shiqu Li

We propose a simple universal (that is, distribution--free) steganographic system in which covertexts with and without hidden texts are statistically indistinguishable. The stegosystem can be applied to any source generating i.i.d.…

Cryptography and Security · Computer Science 2007-05-23 Boris Ryabko , Daniil Ryabko

Scene Text Recognition (STR) is difficult because of the variations in text styles, shapes, and backgrounds. Though the integration of linguistic information enhances models' performance, existing methods based on either permuted language…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Xiaomeng Yang , Zhi Qiao , Jin Wei , Dongbao Yang , Yu Zhou

Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet principled explanations for their underlying mechanisms and several phenomena, such as scaling laws, hallucinations, and related behaviors,…

Artificial Intelligence · Computer Science 2025-11-11 Zhixuan Pan , Shaowen Wang , Jian Li

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

Information Retrieval · Computer Science 2023-11-21 Tong Wu , Yulei Qin , Enwei Zhang , Zihan Xu , Yuting Gao , Ke Li , Xing Sun

In error correction code based image steganography, embedding using large length codes have not been researched extensively. This is due to the fact that the embedding efficiency decreases as the length becomes sufficiently larger and the…

Information Theory · Computer Science 2019-04-12 Suah Kim , Vasily Sachnev , Hyoung Joong Kim

Estimating the difficulty of input questions as perceived by large language models (LLMs) is essential for accurate performance evaluation and adaptive inference. Existing methods typically rely on repeated response sampling, auxiliary…

Computation and Language · Computer Science 2025-09-17 Yubo Zhu , Dongrui Liu , Zecheng Lin , Wei Tong , Sheng Zhong , Jing Shao

We introduce AI-Kolmogorov, a novel framework for Symbolic Density Estimation (SymDE). Symbolic regression (SR) has been effectively used to produce interpretable models in standard regression settings but its applicability to density…

Machine Learning · Computer Science 2026-04-20 Angelo Rajendram , Xieting Chu , Vijay Ganesh , Max Fieg , Aishik Ghosh