Linguistic Steganography Based on Automatically Generated Paraphrases Using Recurrent Neural Networks

Deepthi, Godavarthi; SriLakshmi, N. Vijaya; Mounika, P.; Govardhani, U.; Prassanna, P. Lakshmi; Kavitha, S.; Kumar, Abhishek

doi:10.1007/978-981-16-1866-6_55

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The candidate pool was constructed based on probability difference instead of greedy sampling, and entropy coding was applied to embed secret information. Furthermore, Yi et al [31] proposed a novel linguistic steganographic method which enables the receiver to collect the tokens of the specific positions to directly constitute the secret message in a seemingly-natural steganographic text generated by the off-the-shelf BERT model equipped with Gibbs sampling. Deepthi et al [32] used support vector machine (SVM), recurrent neural network (RNN), and CNN to provide secure data with confidentiality and integrity.…”

Section: Related Workmentioning

confidence: 99%

Linguistic Steganalysis via Fusing Multi-Granularity Attentional Text Features

et al. 2023

View full text Add to dashboard Cite

Deep learning based language models have improved generation-based linguistic steganography, posing a huge challenge for linguistic steganalysis. The existing neural-network-based linguistic steganalysis methods are incompetent to deal with complicated text because they only extract single-granularity features such as global or local text features. To fuse multi-granularity text features, we present a novel linguistic steganalysis method based on attentional bidirectional long-shortterm-memory (BiLSTM) and short-cut dense convolutional neural network (CNN). The BiLSTM equipped with the scaled dot-product attention mechanism is used to capture the long dependency representations of the input sentence. The CNN with the short-cut and dense connection is exploited to extract sufficient local semantic features from the word embedding matrix. We connect two structures in parallel, concatenate the long dependency representations and the local semantic features, and classify the stego and cover texts. The results of comparative experiments demonstrate that the proposed method is superior to the state-of-the-art linguistic steganalysis.

show abstract

Section: Related Workmentioning

confidence: 99%

Linguistic Steganalysis via Fusing Multi-Granularity Attentional Text Features

et al. 2023

View full text Add to dashboard Cite

show abstract

“…To address the issue of semantical irrelevance, some generative steganography models using statistical language models emerged, such as using n-gram models [ 13 ] or Markov chains [ 14 ] to model semantical features. Due to the difficulty of semantical modeling, some statistical models are applied to specific genres such as short jokes [ 15 ], emails [ 16 ], and poetry [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

A novel method for linguistic steganography by English translation using attention mechanism and probability distribution theory

Lin,

Wang

2024

PLoS ONE

View full text Add to dashboard Cite

To enhance our ability to model long-range semantical dependencies, we introduce a novel approach for linguistic steganography through English translation. This method leverages attention mechanisms and probability distribution theory, known as NMT-stega (Neural Machine Translation-steganography). Specifically, to optimize translation accuracy and make full use of valuable source text information, we employ an attention-based NMT model as our translation technique. To address potential issues related to the degradation of text quality due to secret information embedding, we have devised a dynamic word pick policy based on probability variance. This policy adaptively constructs an alternative set and dynamically adjusts embedding capacity at each time step, guided by variance thresholds. Additionally, we have incorporated prior knowledge into the model by introducing a hyper-parameter that balances the contributions of the source and target text when predicting the embedded words. Extensive ablation experiments and comparative analyses, conducted on a large-scale Chinese-English corpus, validate the effectiveness of the proposed method across several critical aspects, including embedding rate, text quality, anti-steganography, and semantical distance. Notably, our numerical results demonstrate that the NMT-stega method outperforms alternative approaches in anti-steganography tasks, achieving the highest scores in two steganalysis models, NFZ-WDA (with score of 53) and LS-CNN (with score of 56.4). This underscores the superiority of NMT-stega in the anti-steganography attack task. Furthermore, even when generating longer sentences, with average lengths reaching 47 words, our method maintains strong semantical relationships, as evidenced by a semantic distance of 87.916. Moreover, we evaluate the proposed method using two metrics, Bilingual Evaluation Understudy and Perplexity, and achieve impressive scores of 42.103 and 23.592, respectively, highlighting its exceptional performance in the machine translation task.

show abstract