Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yihao, Song, Ruiqi, Li, Lingxiao, Zhang, Ru, Liu, Jianyi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912298024566784
author Wang, Yihao
Song, Ruiqi
Li, Lingxiao
Zhang, Ru
Liu, Jianyi
author_facet Wang, Yihao
Song, Ruiqi
Li, Lingxiao
Zhang, Ru
Liu, Jianyi
contents Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool, allocating the one coding to all tokens, which results in identical selection likelihoods. This approach leads to the selection of low-CP tokens, degrading the quality of stegos and making them more detectable. This paper proposes a scheme based on the interval allocated, called DAIRstega. DAIRstega first uses a portion of the read secret to build the roulette area. Then, this scheme uses the idea of the roulette wheel and takes the CPs of tokens as the main basis for allocating the roulette area (i.e., the interval length). Thus, tokens with larger CPs are allocated more area. The secret will have an increased likelihood of selecting a token with a higher CP. During allocation, we designed some allocation functions and three constraints to optimize the process. Additionally, DAIRstega supports prompt-based controllable generation of stegos. Rich experiments show that the proposed embedding way and DAIRstega perform better than the existing ways and baselines, which shows strong perceptual, statistical, and semantic concealment, as well as anti-steganalysis ability. It can also generate high-quality longer stegos, addressing the deficiencies in this task. DAIRstega is confirmed to have potential as a secure watermarking, offering insights for its development.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15656
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel
Wang, Yihao
Song, Ruiqi
Li, Lingxiao
Zhang, Ru
Liu, Jianyi
Computation and Language
Existing linguistic steganography schemes often overlook the conditional probability (CP) of tokens in the candidate pool, allocating the one coding to all tokens, which results in identical selection likelihoods. This approach leads to the selection of low-CP tokens, degrading the quality of stegos and making them more detectable. This paper proposes a scheme based on the interval allocated, called DAIRstega. DAIRstega first uses a portion of the read secret to build the roulette area. Then, this scheme uses the idea of the roulette wheel and takes the CPs of tokens as the main basis for allocating the roulette area (i.e., the interval length). Thus, tokens with larger CPs are allocated more area. The secret will have an increased likelihood of selecting a token with a higher CP. During allocation, we designed some allocation functions and three constraints to optimize the process. Additionally, DAIRstega supports prompt-based controllable generation of stegos. Rich experiments show that the proposed embedding way and DAIRstega perform better than the existing ways and baselines, which shows strong perceptual, statistical, and semantic concealment, as well as anti-steganalysis ability. It can also generate high-quality longer stegos, addressing the deficiencies in this task. DAIRstega is confirmed to have potential as a secure watermarking, offering insights for its development.
title Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel
topic Computation and Language
url https://arxiv.org/abs/2401.15656