High-Performance Linguistic Steganalysis, Capacity Estimation and Steganographic Positioning

Zou, Jiajun; Yang, Zhongliang; Zhang, Siyu; Rehman, Sadaqat ur; Huang, Yudong

doi:10.1007/978-3-030-69449-4_7

Cited by 20 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiao et al [26] took this a step further by introducing a multi-head attention mechanism, connecting word representations with a multi-headed self-attentive representation for further classification. Subsequently, Zou et al [27] employed Bidirectional Encoder Representation from Transformers (BERT) and Global Vectors for Word Representation (Glove) to capture inter-sentence contextual association relationships, then extracted context information using Bi-LSTM and finally obtained the sensitive semantic features via the attention mechanism for steganographic text detection. Xu et al [28] employed a pre-trained BERT language model to obtain initial contextually relevant word representation, after which the extracted features were fed into an LSTM with attention to obtain the final sentence representation used to classify the detected texts.…”

Section: Related Workmentioning

confidence: 99%

A General Linguistic Steganalysis Framework Using Multi-Task Learning

Xiang¹,

Wang²,

Liu³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Prevailing linguistic steganalysis approaches focus on learning sensitive features to distinguish a particular category of steganographic texts from non-steganographic texts, by performing binary classification. While it remains an unsolved problem and poses a significant threat to the security of cyberspace when various categories of non-steganographic or steganographic texts coexist. In this paper, we propose a general linguistic steganalysis framework named LS-MTL, which introduces the idea of multi-task learning to deal with the classification of various categories of steganographic and non-steganographic texts. LS-MTL captures sensitive linguistic features from multiple related linguistic steganalysis tasks and can concurrently handle diverse tasks with a constructed model. In the proposed framework, convolutional neural networks (CNNs) are utilized as private base models to extract sensitive features for each steganalysis task. Besides, a shared CNN is built to capture potential interaction information and share linguistic features among all tasks. Finally, LS-MTL incorporates the private and shared sensitive features to identify the detected text as steganographic or non-steganographic. Experimental results demonstrate that the proposed framework LS-MTL outperforms the baseline in the multi-category linguistic steganalysis task, while average Acc, Pre, and Rec are increased by 0.5%, 1.4%, and 0.4%, respectively. More ablation experimental results show that LS-MTL with the shared module has robust generalization capability and achieves good detection performance even in the case of spare data.

show abstract

Section: Related Workmentioning

confidence: 99%

A General Linguistic Steganalysis Framework Using Multi-Task Learning

Xiang¹,

Wang²,

Liu³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Niu et al [35] combined a bidirectional LSTM (Bi-LSTM) neural network and CNN network to capture local and long-term semantic features. Zou et al [59] employed the BERT and Glove component to extract the word features, then a Bi-LSTM with attention mechanism was used to extract contextual relation. Peng et al [36] proposed a real-time text steganalysis method and used transfer learning to improve detection accuracy.…”

Section: Text Steganalysismentioning

confidence: 99%

Few-shot Text Steganalysis Based on Attentional Meta-learner

Wen

Zhang

et al. 2022

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security

View full text Add to dashboard Cite

Text steganalysis is a technique to distinguish between steganographic text and normal text via statistical features. Current stateof-the-art text steganalysis models have two limitations. First, they need su cient amounts of labeled data for training. Second, they lack the generalization ability on di erent detection tasks. In this paper, we propose a meta-learning framework for text steganalysis in the few-shot scenario to ensure model fast-adaptation between tasks. A general feature extractor based on BERT is applied to extract universal features among tasks, and a meta-learner based on attentional Bi-LSTM is employed to learn task-speci c representations. A classi er trained on the support set calculates the prediction loss on the query set with a few samples to update the meta-learner. Extensive experiments show that our model can adapt fast among di erent steganalysis tasks through extremely few-shot samples, signi cantly improving detection performance compared with the state-of-the-art steganalysis models and other meta-learning methods. CCS CONCEPTS• Security and privacy → Human and societal aspects of security and privacy; • Computing methodologies → Natural language processing.

show abstract

“…However, this type of calculation method lacks the structure information between entities, making it difficult to measure the similarity between the two cases from a semantic point of view. Another option to define similarity measures for cases is through the use of embeddings (Zou et al, 2020). For example, Xu et al (2021) used the word2vec model to obtain semantic information from fault data for fault classification.…”

Section: Introductionmentioning

confidence: 99%

Finite-element analysis case retrieval based on an ontology semantic tree

Xu,

Cheng,

Xiao

et al. 2024

AIEDAM

View full text Add to dashboard Cite

The widespread use of finite-element analysis (FEA) in industry has led to a large accumulation of cases. Leveraging past FEA cases can improve accuracy and efficiency in analyzing new complex tasks. However, current engineering case retrieval methods struggle to measure semantic similarity between FEA cases. Therefore, this article proposed a method for measuring the similarity of FEA cases based on ontology semantic trees. FEA tasks are used as indexes for FEA cases, and an FEA case ontology is constructed. By using named entity recognition technology, pivotal entities are extracted from FEA tasks, enabling the instantiation of the FEA case ontology and the creation of a structured representation for FEA cases. Then, a multitree algorithm is used to calculate the semantic similarity of FEA cases. Finally, the correctness of this method was confirmed through an FEA case retrieval experiment on a pressure vessel. The experimental results clearly showed that the approach outlined in this article aligns more closely with expert ratings, providing strong validation for its effectiveness.

show abstract

High-Performance Linguistic Steganalysis, Capacity Estimation and Steganographic Positioning

Cited by 20 publications

References 26 publications

A General Linguistic Steganalysis Framework Using Multi-Task Learning

A General Linguistic Steganalysis Framework Using Multi-Task Learning

Few-shot Text Steganalysis Based on Attentional Meta-learner

Finite-element analysis case retrieval based on an ontology semantic tree

Contact Info

Product

Resources

About