Salvato in:
Dettagli Bibliografici
Autori principali: Hellmeier, Malte, Norkowski, Hendrik, Schrewe, Ernst-Christoph, Qarawlus, Haydar, Howar, Falk
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.12710
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911112774025216
author Hellmeier, Malte
Norkowski, Hendrik
Schrewe, Ernst-Christoph
Qarawlus, Haydar
Howar, Falk
author_facet Hellmeier, Malte
Norkowski, Hendrik
Schrewe, Ernst-Christoph
Qarawlus, Haydar
Howar, Falk
contents Large language models (LLMs) have gained significant popularity in recent years. Differentiating between a text written by a human and one generated by an LLM has become almost impossible. Information-hiding techniques such as digital watermarking or steganography can help by embedding information inside text in a form that is unlikely to be noticed. However, existing techniques, such as linguistic-based or format-based methods, change the semantics or cannot be applied to pure, unformatted text. In this paper, we introduce a novel method for information hiding called Innamark, which can conceal any byte-encoded sequence within a sufficiently long cover text. This method is implemented as a multi-platform library using the Kotlin programming language, which is accompanied by a command-line tool and a web interface. By substituting conventional whitespace characters with visually similar Unicode whitespace characters, our proposed scheme preserves the semantics of the cover text without changing the number of characters. Furthermore, we propose a specified structure for secret messages that enables configurable compression, encryption, hashing, and error correction. An experimental benchmark comparison on a dataset of 1 000 000 Wikipedia articles compares ten algorithms. The results demonstrate the robustness of our proposed Innamark method in various applications and the imperceptibility of its watermarks to humans. We discuss the limits to the embedding capacity and robustness of the algorithm and how these could be addressed in future work.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12710
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Innamark: A Whitespace Replacement Information-Hiding Method
Hellmeier, Malte
Norkowski, Hendrik
Schrewe, Ernst-Christoph
Qarawlus, Haydar
Howar, Falk
Cryptography and Security
Artificial Intelligence
Software Engineering
Large language models (LLMs) have gained significant popularity in recent years. Differentiating between a text written by a human and one generated by an LLM has become almost impossible. Information-hiding techniques such as digital watermarking or steganography can help by embedding information inside text in a form that is unlikely to be noticed. However, existing techniques, such as linguistic-based or format-based methods, change the semantics or cannot be applied to pure, unformatted text. In this paper, we introduce a novel method for information hiding called Innamark, which can conceal any byte-encoded sequence within a sufficiently long cover text. This method is implemented as a multi-platform library using the Kotlin programming language, which is accompanied by a command-line tool and a web interface. By substituting conventional whitespace characters with visually similar Unicode whitespace characters, our proposed scheme preserves the semantics of the cover text without changing the number of characters. Furthermore, we propose a specified structure for secret messages that enables configurable compression, encryption, hashing, and error correction. An experimental benchmark comparison on a dataset of 1 000 000 Wikipedia articles compares ten algorithms. The results demonstrate the robustness of our proposed Innamark method in various applications and the imperceptibility of its watermarks to humans. We discuss the limits to the embedding capacity and robustness of the algorithm and how these could be addressed in future work.
title Innamark: A Whitespace Replacement Information-Hiding Method
topic Cryptography and Security
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2502.12710